File size: 714 Bytes
1801c3b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 |
import requests
from PIL import Image
from transformers import CLIPModel, CLIPProcessor
model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)
inputs = processor(
text=["a photo of a cat", "a photo of a dog"],
images=image,
return_tensors="pt",
padding=True,
)
outputs = model(**inputs)
logits_per_image = outputs.logits_per_image # this is the image-text similarity score
probs = logits_per_image.softmax(
dim=1
) # we can take the softmax to get the label probabilities
print(probs)
|