From e21127a3fc4797805d49ae2d95fc7ed6f94ac456 Mon Sep 17 00:00:00 2001 From: skal Date: Sun, 15 Feb 2026 19:12:58 +0100 Subject: feat(cnn): add CNN v3 directory structure with training data Initialize CNN v3 subdirectory with training pipeline layout: - docs/, scripts/, shaders/, src/, tools/, weights/ for organization - training/input/ with sample images - training/target_1/, target_2/ for multi-style training - README.md documenting structure Training images tracked in repo for easy collaboration. Co-Authored-By: Claude Sonnet 4.5 --- cnn_v3/README.md | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) create mode 100644 cnn_v3/README.md (limited to 'cnn_v3/README.md') diff --git a/cnn_v3/README.md b/cnn_v3/README.md new file mode 100644 index 0000000..fdbf648 --- /dev/null +++ b/cnn_v3/README.md @@ -0,0 +1,36 @@ +# CNN v3 + +Enhanced CNN post-processing with next-generation features. + +## Directory Structure + +``` +cnn_v3/ +├── docs/ # Documentation and design notes +├── scripts/ # Training and build automation scripts +├── shaders/ # WGSL compute shaders +├── src/ # C++ implementation +├── tools/ # Testing and validation tools +├── training/ # Training pipeline +│ ├── input/ # Source images for training +│ ├── target_1/ # Style 1 target images +│ └── target_2/ # Style 2 target images +└── weights/ # Trained model weights (binary format) +``` + +## Training Data + +Training images are tracked in the repository: +- `training/input/` - Original input images +- `training/target_1/` - First style transformation targets +- `training/target_2/` - Second style transformation targets + +Multiple target directories allow training different stylistic transformations from the same input set. + +Add images directly to these directories and commit them. + +## Status + +**TODO:** Define CNN v3 architecture and feature set. + +See `cnn_v2/` for reference implementation. -- cgit v1.2.3