demo.git/training/input, branch main
Vide-coded 64k demo system
https://git.taar-o.com/demo.git/atom?h=main
2026-02-10T09:27:44Z
feat: Add coordinate-aware CNN layer 0 for position-dependent stylization
2026-02-10T09:27:44Z
skal
pascal.massimino@gmail.com
2026-02-10T09:27:44Z
urn:sha1:96a349b9874c6cdaac525ba062a0f4f90c9bc3ed
- 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>