| Age | Commit message (Collapse) | Author | |
|---|---|---|---|
| 17 hours | fix(cnn_v3): remove dec0 ReLU, load FiLM MLP at runtime | skal | |
| Two bugs blocking training convergence: 1. dec0 ReLU before sigmoid constrained output to [0.5,1.0] — network could never produce dark pixels. Removed F.relu in train_cnn_v3.py and max(0,…) in cnn_v3_dec0.wgsl. Test vectors regenerated. 2. set_film_params() used hardcoded heuristics instead of the trained MLP. Added CNNv3FilmMlp struct + load_film_mlp() to cnn_v3_effect.h/.cc. MLP auto-loaded from ASSET_WEIGHTS_CNN_V3_FILM_MLP at construction; Linear(5→16)→ReLU→Linear(16→72) runs CPU-side each frame. 36/36 tests pass. Parity max_err=4.88e-4 unchanged. handoff(Gemini): retrain from scratch — needs ≥50 samples (currently 11). See cnn_v3/docs/HOWTO.md §2-3. | |||
| 41 hours | update the weights | skal | |
| 42 hours | feat(cnn_v3): upgrade architecture to enc_channels=[8,16] | skal | |
| Double encoder capacity: enc0 4→8ch, enc1 8→16ch, bottleneck 16→16ch, dec1 32→8ch, dec0 16→4ch. Total weights 2476→7828 f16 (~15.3 KB). FiLM MLP output 40→72 params (L1: 16×40→16×72). 16-ch textures split into _lo/_hi rgba32uint pairs (enc1, bottleneck). enc0 and dec1 textures changed from rgba16float to rgba32uint (8ch). GBUF_RGBA32UINT node gains CopySrc for parity test readback. - WGSL shaders: all 5 passes rewritten for new channel counts - C++ CNNv3Effect: new weight offsets/sizes, 8ch uniform structs - Web tool (shaders.js + tester.js): matching texture formats and bindings - Parity test: readback_rgba32uint_8ch helper, updated vector counts - Training scripts: default enc_channels=[8,16], updated docstrings - Docs + architecture PNG regenerated handoff(Gemini): CNN v3 [8,16] upgrade complete. All code, tests, web tool, training scripts, and docs updated. Next: run training pass. | |||
| 3 days | update weights | skal | |
| 3 days | update weights | skal | |
| 5 days | feat(cnn_v3): wire trained weights into CNNv3Effect + add timeline test sequence | skal | |
| - CNNv3Effect constructor loads ASSET_WEIGHTS_CNN_V3 via GetAsset on startup - seq_compiler.py: CLASS_TO_HEADER supports full #include paths for cnn_v3/ classes - timeline.seq: add cnn_v3_test sequence at 48s (GBufferEffect → CNNv3Effect) - test_cnn_v3_parity: zero_weights test now explicitly uploads zeros to override asset handoff(Gemini): CNNv3Effect ready; export weights to workspaces/main/weights/ and seek to 48s to test | |||
 |
index : demo.git | |
| Vide-coded 64k demo system |
| summaryrefslogtreecommitdiff |