mobileclip2_coca_dfn2b_s13b_mscoco38k_s12m_context77

Name: mobileclip2_coca_dfn2b_s13b_mscoco38k_s12m_context77
Author: apple

2.0B

—

apple

Other

OTHER

2B params

New

6 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

5GB+ RAM

Mobile

Laptop

Server

Quick Summary

MobileCLIP2: Improving Multi-Modal Reinforced Training MobileCLIP2 was introduced in MobileCLIP2: Improving Multi-Modal Reinforced Training (TMLR August 2025 F...

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

2GB+ RAM

Code Examples

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

pythonpytorch

import torch
import open_clip
from PIL import Image

model, _, preprocess = open_clip.create_model_and_transforms('coca_ViT-L-14', pretrained='/path/to/mobileclip2_coca.pt')
model.eval()

image = preprocess(Image.open("docs/fig_accuracy_latency.png").convert('RGB')).unsqueeze(0)

with torch.no_grad(), torch.cuda.amp.autocast():
    syn_text = model.generate(
        image,
        generation_type="top_p",
        top_p=0.9,
        fixed_output_length=True
    )[0]
    syn_text = open_clip.decode(syn_text).split("<end_of_text>")[0].split("<start_of_text>")[-1].split(".")[0].rstrip()
print("Caption:", syn_text)

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.