Course Roadmap Mapping
This weekβs work in the broader GFM plan.
Week | Stage | Focus | You will build (geogfm) | Library tools | Outcome |
---|---|---|---|---|---|
10 | Stage 3: Apply & Deploy | Presentations & Synthesis | Project deliverables (no new geogfm code required) |
β | Present MVP builds, analysis, transition plan |
Weekly goals
- Synthesize architecture, training, and evaluation learnings
- Present MVP results and insights
- Outline next steps with Prithvi/scale-up
Session Outline
- Concepts β Components mapping
- Model architecture β
models/gfm_vit.py
- Pretraining objective β
models/gfm_mae.py
+modules/losses/mae_loss.py
- Training loop β
training/{optimizer.py, loop.py}
- Evaluation β
evaluation/{visualization.py, metrics.py}
- Applied tasks β
tasks/{classification.py, segmentation.py}
- Inference β
inference/{sliding_window.py, tiling.py}
- Model architecture β
- Deliverables checklist
- Slides with pipeline diagram and key code references
- Short demo: load a small batch, run MAE forward, show recon
- One analysis figure (recon grid or PSNR curve)
- What you would swap to scale (timm blocks, TorchGeo datasets, FlashAttention, HF hub)