Spaces:
Sleeping
Sleeping
metadata
title: Beit-Retinal
emoji: π
colorFrom: red
colorTo: green
sdk: docker
pinned: false
license: mit
short_description: Training model for some retina dataset
RETFound MAE β 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 /predictβ 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/.