diff options
| author | skal <pascal.massimino@gmail.com> | 2026-03-25 08:27:39 +0100 |
|---|---|---|
| committer | skal <pascal.massimino@gmail.com> | 2026-03-25 08:27:39 +0100 |
| commit | 3e4fece8fce11b368b4c7bab284242bf18e6a0b1 (patch) | |
| tree | 108682f727f7668e1df346563f4576d7e567dcd2 /cnn_v3/training/dataset/simple/sample_009/albedo.png | |
| parent | 64095c683f15e8bd7c19d32041fcc81b1bd6c214 (diff) | |
feat(cnn_v3/training): add --single-sample option + doc fixes
- train_cnn_v3.py: --single-sample <dir> implies --full-image + --batch-size 1
- cnn_v3_utils.py: CNNv3Dataset accepts single_sample= kwarg (explicit override)
- HOWTO.md: document --single-sample workflow, fix pack_photo_sample.py usage (--target required)
- HOW_TO_CNN.md: fix GBufferEffect seq input (prev_cnn→source), fix binary name (demo→demo64k), add --resume to flag table, remove stale "pack without target" block
handoff(Gemini): --single-sample <dir> added to train_cnn_v3.py; docs audited and corrected
Diffstat (limited to 'cnn_v3/training/dataset/simple/sample_009/albedo.png')
0 files changed, 0 insertions, 0 deletions