Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| from transformers import AutoProcessor, AutoTokenizer, AutoImageProcessor, AutoModelForCausalLM, BlipForConditionalGeneration, VisionEncoderDecoderModel | |
| import torch | |
| torch.hub.download_url_to_file('http://images.cocodataset.org/val2017/000000039769.jpg', 'cats.jpg') | |
| torch.hub.download_url_to_file('https://huggingface.co/datasets/nielsr/textcaps-sample/resolve/main/stop_sign.png', 'stop_sign.png') | |
| torch.hub.download_url_to_file('https://cdn.openai.com/dall-e-2/demos/text2im/astronaut/horse/photo/0.jpg', 'astronaut.jpg') | |
| git_processor = AutoProcessor.from_pretrained("microsoft/git-large-coco") | |
| git_model = AutoModelForCausalLM.from_pretrained("microsoft/git-large-coco") | |
| device = "cuda" if torch.cuda.is_available() else "cpu" | |
| git_model.to(device) | |
| def generate_caption(processor, model, image): | |
| inputs = processor(images=image, return_tensors="pt").to(device) | |
| generated_ids = model.generate(pixel_values=inputs.pixel_values, max_length=50) | |
| generated_caption = processor.batch_decode(generated_ids, skip_special_tokens=True)[0] | |
| return generated_caption | |
| def generate_captions(image): | |
| return generate_caption(git_processor, git_model, image) | |
| examples = [["cats.jpg"], ["stop_sign.png"], ["astronaut.jpg"]] | |
| outputs = [gr.outputs.Textbox(label="Caption generated by GIT-Large coco")] | |
| title = "Interactive demo: GIT-Large coco image captioning" | |
| description = "GIT-Large coco image captioning" | |
| article = "<p style='text-align: center'><a href='https://huggingface.co/docs/transformers/main/model_doc/blip' target='_blank'>BLIP docs</a> | <a href='https://huggingface.co/docs/transformers/main/model_doc/git' target='_blank'>GIT docs</a></p>" | |
| interface = gr.Interface(fn=generate_captions, | |
| inputs=gr.inputs.Image(type="pil"), | |
| outputs=outputs, | |
| examples=examples, | |
| title=title, | |
| description=description, | |
| article=article, | |
| enable_queue=True) | |
| interface.launch(debug=True) | |