marqo-fashionCLIP

Name: marqo-fashionCLIP
Author: Marqo

22.2K

1 language

FP16

license:apache-2.0

Marqo

Image Model

OTHER

Fair

22K downloads

Community-tested

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

Unknown

Mobile

Laptop

Server

Quick Summary

AI model with specialized capabilities.

Code Examples

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

bash

npm i @huggingface/transformers

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

javascript

import { CLIPTextModelWithProjection, CLIPVisionModelWithProjection, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';

const model_id = 'Marqo/marqo-fashionCLIP';

// Load tokenizer and text model
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const text_model = await CLIPTextModelWithProjection.from_pretrained(model_id);

// Load processor and vision model
const processor = await AutoProcessor.from_pretrained(model_id);
const vision_model = await CLIPVisionModelWithProjection.from_pretrained(model_id);

// Run tokenization
const texts = ['a hat', 'a t-shirt', 'shoes'];
const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });

// Compute text embeddings
const { text_embeds } = await text_model(text_inputs);

// Read image and run processor
const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
const image_inputs = await processor(image);

// Compute vision embeddings
const { image_embeds } = await vision_model(image_inputs);

// Compute similarity scores
const normalized_text_embeds = text_embeds.normalize().tolist();
const normalized_image_embeds = image_embeds.normalize().tolist()[0];

const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
    100.0 * dot(normalized_image_embeds, text_embed)
));
console.log(text_probs);
// [0.9998498302475922, 0.000119267522939106, 0.000030902229468640687]

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.