demo.git - Vide-coded 64k demo system

Age	Commit message (Expand)	Author
59 min.	feat: Add inference mode to train_cnn.py for ground truth generation	skal
64 min.	fix: CNN training normalization pipeline consistency	skal
2 hours	refactor: Optimize CNN normalization to eliminate redundant conversions	skal
3 hours	fix: Support variable kernel sizes in CNN layer generation	skal
4 hours	feat: CNN RGBD→grayscale with 7-channel augmented input	skal
5 hours	udpate	skal
8 hours	feat: Add multi-layer CNN support with framebuffer capture and blend control	skal
10 hours	docs: Update and streamline CNN training documentation	skal
10 hours	feat: Add checkpointing support to CNN training script	skal
10 hours	fix: Auto-expand single kernel size to all layers in training script	skal
11 hours	update target images	skal
11 hours	feat: Add coordinate-aware CNN layer 0 for position-dependent stylization	skal