“Customized OpenCLIP Tokenizer”

[Vaspory]

import torch
import torch.nn.functional as F
from urllib.request import urlopen
from PIL import Image

⚠️ Use our repo's tokenizer implementation at src/convert_upload/open_clip/

from open_clip import create_model_from_pretrained, get_tokenizer

model, preprocess = create_model_from_pretrained('hf-hub:UCSC-VLAA/openvision-vit-large-patch14-224')
tokenizer = get_tokenizer('hf-hub:UCSC-VLAA/openvision-vit-large-patch14-224')

image = Image.open(urlopen(
'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
image = preprocess(image).unsqueeze(0)

text = tokenizer(["a diagram", "a dog", "a cat", "a beignet"], context_length=model.context_length)

with torch.no_grad(), torch.cuda.amp.autocast():
image_features = model.encode_image(image)
text_features = model.encode_text(text)
image_features = F.normalize(image_features, dim=-1)
text_features = F.normalize(text_features, dim=-1)

text_probs = (100.0 * image_features @ text_features.T).softmax(dim=-1)

print("Label probs:", text_probs) # prints: [[0., 0., 0., 1.0]]

src/convert_upload/open_clip/