|
import torch |
|
import time |
|
import clip |
|
from PIL import Image |
|
|
|
device = "cuda" if torch.cuda.is_available() else "cpu" |
|
model, preprocess = clip.load("ViT-B/32", device=device) |
|
|
|
image = preprocess(Image.open("CLIP.png")).unsqueeze(0).to(device) |
|
text = clip.tokenize(["a diagram", "a dog", "a cat"]).to(device) |
|
|
|
start_time = time.time() |
|
|
|
with torch.no_grad(): |
|
image_features = model.encode_image(image) |
|
text_features = model.encode_text(text) |
|
|
|
logits_per_image, logits_per_text = model(image, text) |
|
probs = logits_per_image.softmax(dim=-1).cpu().numpy() |
|
|
|
end_time = time.time() |
|
|
|
print("Label probs:", probs) |
|
|
|
print(f"Prediction time: {end_time - start_time} seconds") |
|
|
