| import streamlit as st | |
| from PIL import Image | |
| import requests | |
| from transformers import CLIPProcessor, CLIPModel | |
| 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) | |
| st.write(outputs) | |