demo.git - Vide-coded 64k demo system

Age	Commit message (Expand)	Author
9 hours	feat: Add inference mode to train_cnn.py for ground truth generation	skal
9 hours	fix: CNN training normalization pipeline consistency	skal
10 hours	refactor: Optimize CNN normalization to eliminate redundant conversions	skal
11 hours	fix: Support variable kernel sizes in CNN layer generation	skal
12 hours	feat: CNN RGBD→grayscale with 7-channel augmented input	skal
16 hours	feat: Add multi-layer CNN support with framebuffer capture and blend control	skal
18 hours	feat: Add checkpointing support to CNN training script	skal
18 hours	fix: Auto-expand single kernel size to all layers in training script	skal
18 hours	feat: Add coordinate-aware CNN layer 0 for position-dependent stylization	skal