| import gradio as gr | |
| from transformers import CLIPProcessor, CLIPModel | |
| model = CLIPModel.from_pretrained("openai/clip-vit-base-patch16") | |
| processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch16") | |
| def calculate_score(image, text): | |
| labels = text.split(";") | |
| labels = [l.strip() for l in labels] | |
| labels = list(filter(None, labels)) | |
| if len(labels) == 0: | |
| return dict() | |
| inputs = processor(text=labels, images=image, return_tensors="pt", padding=True) | |
| outputs = model(**inputs) | |
| logits_per_image = outputs.logits_per_image.detach().numpy() | |
| results_dict = { | |
| label: score / 100.0 for label, score in zip(labels, logits_per_image[0]) | |
| } | |
| return results_dict | |
| if __name__ == "__main__": | |
| cat_example = [ | |
| "cat.jpg", | |
| "a cat stuck in a door; a cat in the air; a cat sitting; a cat standing; a cat is entering the matrix; a cat is entering the void", | |
| ] | |
| demo = gr.Interface( | |
| fn=calculate_score, | |
| inputs=["image", "text"], | |
| outputs="label", | |
| examples=[cat_example], | |
| allow_flagging="never", | |
| description="# CLIP Score", | |
| article="Calculate the [CLIP](https://openai.com/blog/clip/) score of a given image and text", | |
| cache_examples=True, | |
| ) | |
| demo.launch() | |