BrainAge Training Pipeline
GPU-powered training Space for the BrainAge brain-age prediction model.
Workflow:
- Downloads preprocessed
.ptcache from BrainAge-Golden-Preprocessed - Generates stratified train/val/test split
- Phase A: Lifespan pretraining (all ages, 60 epochs)
- Phase B: Pediatric fine-tuning (0–25y, 30 epochs)
- Pushes checkpoints and logs to BrainAge-SFCN
Required secrets: HF_TOKEN (write access to model repo)
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support