demo.git - Vide-coded 64k demo system

Age	Commit message (Collapse)	Author
10 hours	docs: Update and streamline CNN training documentation	skal
	- Document coordinate-aware layer 0 architecture - Add checkpointing examples and options table - Consolidate training workflow with practical examples - Clarify CoordConv2d usage and size impact - Streamline training/README.md structure Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
11 hours	feat: Add checkpointing support to CNN training script	skal
	- Save checkpoints every N epochs (--checkpoint-every) - Resume from checkpoint (--resume) - Store model, optimizer, epoch, loss, and architecture info - Auto-create checkpoint directory Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
11 hours	fix: Auto-expand single kernel size to all layers in training script	skal
	Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
11 hours	update target images	skal

11 hours	feat: Add coordinate-aware CNN layer 0 for position-dependent stylization	skal
	- Implement CoordConv2d custom layer accepting (x,y) patch center - Split layer 0 weights: rgba_weights (9x mat4x4) + coord_weights (mat2x4) - Add *_with_coord() functions to 3x3/5x5/7x7 convolution shaders - Update training script to generate coordinate grid and export split weights - Regenerate placeholder weights with new format Size impact: +32B coord weights + ~100B shader code = +132B total All 36 tests passing (100%) handoff(Claude): CNN coordinate awareness implemented, ready for training Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>