| Age | Commit message (Expand) | Author |
|---|---|---|
| 28 hours | fix: Correct UV coordinate computation to match PyTorch linspace | skal |
| 28 hours | fix: Add clamp to CNN final layer to match PyTorch training | skal |
| 28 hours | refactor: Optimize CNN grayscale computation | skal |
| 28 hours | update train_cnn.py and shader | skal |
| 29 hours | feat: Add inference mode to train_cnn.py for ground truth generation | skal |
| 29 hours | fix: CNN training normalization pipeline consistency | skal |
| 30 hours | refactor: Optimize CNN normalization to eliminate redundant conversions | skal |
| 31 hours | fix: Support variable kernel sizes in CNN layer generation | skal |
| 32 hours | feat: CNN RGBD→grayscale with 7-channel augmented input | skal |
| 36 hours | feat: Add multi-layer CNN support with framebuffer capture and blend control | skal |
| 38 hours | feat: Add checkpointing support to CNN training script | skal |
| 38 hours | fix: Auto-expand single kernel size to all layers in training script | skal |
| 38 hours | feat: Add coordinate-aware CNN layer 0 for position-dependent stylization | skal |
 |
index : demo.git | |
| Vide-coded 64k demo system |
| summaryrefslogtreecommitdiff |