pip install open_clip_torch
import torch
from PIL import Image
import open_clip
model, _, preprocess = open_clip.create_model_and_transforms('ViT-B-32', pretrained='laion2b_s34b_b79k')
model.eval() # model in train mode by default, impacts some models with BatchNorm or stochastic depth active
tokenizer = open_clip.get_tokenizer('ViT-B-32')
image = preprocess(Image.open("docs/CLIP.png")).unsqueeze(0)
text = tokenizer(["a diagram", "a dog", "a cat"])
with torch.no_grad()… See the full description on the dataset page:
https://huggingface.co/datasets/andrey56200702/Libidogggg.
