diff options
Diffstat (limited to 'TODO.md')
| -rw-r--r-- | TODO.md | 11 |
1 files changed, 4 insertions, 7 deletions
@@ -79,13 +79,10 @@ 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()` -**FiLM MLP training** (blocks meaningful Phase 4 output): -- Needs `cnn_v3/training/train_cnn_v3.py` — not yet written -- MLP: `Linear(5→16) → ReLU → Linear(16→48)` trained jointly with U-Net -- Input: `[beat_phase, beat_time/8, audio_intensity, style_p0, style_p1]` -- Output: γ/β for enc0(4ch) + enc1(8ch) + dec1(4ch) + dec0(4ch) = 40 floats -- Trained weights (~3 KB f16) stored in `.bin` after conv weights; loaded at runtime -- See `cnn_v3/docs/CNN_V3.md` §5 for full MLP spec and §11 for training pipeline plan +**Next: export + real training run** +- `train_cnn_v3.py` + `cnn_v3_utils.py` written (Phase 6 training script done) +- Still needed: `export_cnn_v3_weights.py` — convert trained `.pth` → `.bin` (f16) +- See `cnn_v3/docs/HOWTO.md` §3 for training commands ## Future: CNN v2 8-bit Quantization |