vilt-b32-finetuned-coco

from transformers import ViltProcessor, ViltForImageAndTextRetrieval
import requests
from PIL import Image

url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)
texts = ["An image of two cats chilling on a couch", "A football player scoring a goal"]

processor = ViltProcessor.from_pretrained("dandelin/vilt-b32-finetuned-coco")
model = ViltForImageAndTextRetrieval.from_pretrained("dandelin/vilt-b32-finetuned-coco")

# prepare inputs
encoding = processor(image, text, return_tensors="pt")

# forward pass
scores = dict()
for text in texts:
    encoding = processor(image, text, return_tensors="pt")
    outputs = model(**encoding)
    scores[text] = outputs.logits[0, :].item()

@misc{kim2021vilt,
      title={ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision}, 
      author={Wonjae Kim and Bokyung Son and Ildoo Kim},
      year={2021},
      eprint={2102.03334},
      archivePrefix={arXiv},
      primaryClass={stat.ML}
}