diff options
Diffstat (limited to 'TODO.md')
| -rw-r--r-- | TODO.md | 11 |
1 files changed, 8 insertions, 3 deletions
@@ -79,9 +79,14 @@ PyTorch / HTML WebGPU / C++ WebGPU. 5. ✅ Parity validation: test vectors + `test_cnn_v3_parity.cc`. max_err=4.88e-4 (≤1/255). - Key fix: intermediate nodes at fractional resolutions (W/2, W/4) via `NodeRegistry::default_width()/default_height()` -**Next: export + real training run** -- `train_cnn_v3.py` + `cnn_v3_utils.py` written (Phase 6 training script done) -- ✅ `export_cnn_v3_weights.py` — convert trained `.pth` → `.bin` (f16) +6. ✅ Training script: `train_cnn_v3.py` + `cnn_v3_utils.py` written + - ✅ `export_cnn_v3_weights.py` — convert trained `.pth` → `.bin` (f16) +7. ✅ Validation tools: + - `GBufViewEffect` — C++ 4×5 channel grid (all 20 G-buffer channels) + - Web tool "Load sample directory" — G-buffer pack → CNN inference → PSNR + - See `cnn_v3/docs/HOWTO.md` §9 + +**Next: run a real training pass** - See `cnn_v3/docs/HOWTO.md` §3 for training commands ## Future: CNN v3 "2D Mode" (G-buffer-free) |