Spaces:
Sleeping
Sleeping
|
Download README.md from habeebCycle/Beit-Retinal: direct link, hf CLI and curl.
- Browser
- Download file 774 Bytes
-
https://huggingface.co/spaces/habeebCycle/Beit-Retinal/resolve/main/README.md
- Command line
-
hf download hf://spaces/habeebCycle/Beit-Retinal/README.md
-
curl -L -o README.md https://huggingface.co/spaces/habeebCycle/Beit-Retinal/resolve/main/README.md
774 Bytes
| title: Beit-Retinal | |
| emoji: ๐ | |
| colorFrom: red | |
| colorTo: green | |
| sdk: docker | |
| pinned: false | |
| license: mit | |
| short_description: Training model for some retina dataset | |
| # RETFound MAE โ Hugging Face Space (FastAPI): Train + Inference | |
| This Space lets you upload a zipped ImageFolder dataset, fine-tune a classifier head on top of RETFound MAE, run predictions, and push the trained model to the Hub. | |
| ## Endpoints | |
| - `POST /predict` โ form-data file=`image.jpg` | |
| ## Env Vars | |
| - `HF_BASE_MODEL_REPO` (e.g., `username/retfound-model`) | |
| ## Dataset format | |
| ``` | |
| zip-root/ | |
| train/ | |
| ClassA/*.jpg | |
| ClassB/*.jpg | |
| val/ | |
| ClassA/*.jpg | |
| ClassB/*.jpg | |
| ``` | |
| ## Notes | |
| - GPU recommended. If CPU-only, reduce batch size. | |
| - Validation accuracy is reported; best checkpoint saved to `checkpoints/`. | |