demo.git - Vide-coded 64k demo system

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