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()
tokenizer = open_clip.get_tokenizer('ViT-B-32')

image = preprocess(Image.open("data/Flicker8k_Dataset/1000268201_693b08cb0e.jpg")).unsqueeze(0)
text = tokenizer(["a little girl climbing into a wooden playhouse", "a dog on the beach", "a cat"])

with torch.no_grad():
    image_features = model.encode_image(image)
    text_features = model.encode_text(text)
    image_features /= image_features.norm(dim=-1, keepdim=True)
    text_features /= text_features.norm(dim=-1, keepdim=True)

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

print("Label probs:", text_probs)