| Age | Commit message (Collapse) | Author |
|---|
|
Renamed files and classes:
- cnn_effect.{h,cc} → cnn_v1_effect.{h,cc}
- CNNEffect → CNNv1Effect
- CNNEffectParams → CNNv1EffectParams
- CNNLayerParams → CNNv1LayerParams
- CNN_EFFECT.md → CNN_V1_EFFECT.md
Updated all references:
- C++ includes and class usage
- CMake source list
- Timeline (workspaces/main/timeline.seq)
- Test file (test_demo_effects.cc)
- Documentation (CLAUDE.md, PROJECT_CONTEXT.md, READMEs)
Tests: 34/34 passing (100%)
|
|
Streamlined and updated all training docs with new patch-based approach.
Changes:
- HOWTO.md: Updated training section with patch/full-image examples
- CNN_EFFECT.md: Streamlined training workflow, added detector info
- training/README.md: Complete rewrite with detector comparison table
New sections:
- Detector comparison (harris, fast, shi-tomasi, gradient)
- Practical examples for different use cases
- Tips for patch size and batch size selection
- Benefits of patch-based training
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
|
|
- 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>
|
|
- 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>
|
