Spaces:
Running
Running
| title: RADIOCAP | |
| emoji: π | |
| colorFrom: purple | |
| colorTo: indigo | |
| sdk: gradio | |
| sdk_version: 5.49.1 | |
| app_file: app.py | |
| pinned: false | |
| license: apache-2.0 | |
| short_description: Radiology interpreter | |
| ## **README.md** | |
| ```md | |
| # RADIOCAP13 β Visual Captioning Model | |
| This Space runs a custom image captioning pipeline using: | |
| - ViT Base (Google) | |
| - Custom BiasDecoder | |
| - Custom 75k vocabulary | |
| ## π Running Locally | |
| ``` | |
| pip install -r requirements.txt | |
| python app.py | |
| ``` | |
| ## πΌοΈ Usage | |
| Upload an image and the model will generate a caption using beam search. | |
| ## π Files | |
| - `app.py` β Gradio interface + model code | |
| - `vocab.json` β tokenizer vocabulary | |
| - `pytorch_model.bin` β trained decoder weights | |
| ``` | |
| --- | |
| If you'd like, I can add: | |
| - `example.jpg` | |
| - automatic CPU/GPU selector badge | |
| - HuggingFace `Space` metadata (`.huggingface.yaml`) | |
| - progress bars / image preview UI | |
| --- | |
| ## **.huggingface.yaml** (Space Metadata) | |
| ```yaml | |
| # RADIOCAP13 Space Metadata | |
| sdk: gradio | |
| sdk_version: 4.0 | |
| python_version: 3.10 | |
| runtime: python3 | |
| # Enable GPU if available | |
| grants: | |
| - gpu: true | |
| app_file: app.py | |
| # Display information on the HF Space page | |
| space_description: | | |
| RADIOCAP13 β A custom image captioning model powered by ViT and a BiasDecoder. | |
| Upload an image and the model generates a caption using beam search. | |
| space_tags: | |
| - image-captioning | |
| - vision | |
| - vit | |
| - pytorch | |
| - gradio | |
| ``` | |
| --- | |
| ## **Example Image (example.jpg)** | |
| Include a placeholder. You can drag an actual sample image later. | |
| ```text | |
| (example.jpg placeholder β include any sample image in your repo) | |
| ``` | |
| --- | |
| ## **Enhanced UI with GPU Status + Progress Bar** | |
| Below is an improved Gradio UI you can swap into `app.py`. | |
| ```python | |
| with gr.Blocks() as demo: | |
| gr.Markdown("# RADIOCAP13 β Image Captioning Demo") | |
| gr.Markdown( | |
| f"**Device:** {'GPU π' if torch.cuda.is_available() else 'CPU π’'}" | |
| ) | |
| with gr.Row(): | |
| img_in = gr.Image(type="pil", label="Upload an Image") | |
| out = gr.Textbox(label="Generated Caption") | |
| btn = gr.Button("Generate Caption") | |
| progress = gr.Markdown("Ready.") | |
| def wrapped_generate(img): | |
| progress.update("Generatingβ¦ please wait β³") | |
| caption = generate_caption(img) | |
| progress.update("Done βοΈ") | |
| return caption | |
| btn.click(wrapped_generate, inputs=img_in, outputs=out) | |
| ``` | |
| --- | |
| ## All enhancements added βοΈ | |
| - Metadata file for HF Space | |
| - GPU badge / indicator | |
| - Progress bar | |
| - Support for example image | |
| - Fully structured Space project | |
| If you want: | |
| π₯ Auto-download model weights from HuggingFace Hub | |
| π₯ Separate tokenizer/model modules | |
| π₯ Add image thumbnails / gallery samples | |
| π₯ Add beam size slider, temperature, etc. | |
| Just say **βadd moreβ** or tell me specific features! | |
| Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference | |