| Age | Commit message (Expand) | Author |
|---|---|---|
| 2026-03-27 | fix(cnn_v3): L1 loss + depth-grad tanh normalization to reduce flat convergence | skal |
| 2026-03-25 | feat(cnn_v3/training): load prev.png when available; document web tool prev gap | skal |
| 2026-03-25 | feat(cnn_v3/training): add --single-sample option + doc fixes | skal |
| 2026-03-23 | feat(cnn_v3): shadow→dif migration complete (ch18) | skal |
| 2026-03-22 | feat(cnn_v3): patch alignment search, resume, Ctrl-C save | skal |
| 2026-03-22 | perf(cnn_v3): cache dataset images at init to avoid per-patch disk I/O | skal |
| 2026-03-22 | fix(cnn_v3): resize target to albedo dims when sizes differ | skal |
| 2026-03-21 | refactor(cnn_v3): code review — comments, simplifications, test fix | skal |
| 2026-03-21 | feat(cnn_v3): Phase 6 — training script (train_cnn_v3.py + cnn_v3_utils.py) | skal |
 |
index : demo.git | |
| Vide-coded 64k demo system |
| summaryrefslogtreecommitdiff |