Spaces:
Paused
Paused
| 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 CLIP_calculate_score(image, text): | |
| words = text.split(";") | |
| words = [w.strip() for w in words] | |
| words = list(filter(None, words)) | |
| if len(words) == 0: | |
| return dict() | |
| inputs = processor(text=words, 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(words, logits_per_image[0]) | |
| } | |
| return results_dict | |
| examples = [ | |
| ["images/girl_and_dog.jpg", "a dog playing in the beach; a dog and a girl playing in the beach; a girl playing in the beach"], | |
| ["images/horse.jpg", "group of horses running; a dog playing; a horse standing"], | |
| ["images/man_and_cat.jpg", "a man and a cat listening to music; a cat; a man"] | |
| ] | |
| demo = gr.Interface( | |
| fn=CLIP_calculate_score, | |
| inputs=["image", "text"], | |
| outputs="label", | |
| examples=examples, | |
| # allow_flagging="never", | |
| # cache_examples=True, | |
| ) | |
| demo.launch() |