diff options
| author | skal <pascal.massimino@gmail.com> | 2026-02-13 16:44:05 +0100 |
|---|---|---|
| committer | skal <pascal.massimino@gmail.com> | 2026-02-13 16:44:05 +0100 |
| commit | 3eed58f0cd602298681a2313946ba2a5824d6c6e (patch) | |
| tree | e4953ce0eb13a578aa564d6edbb63ea6f2827182 | |
| parent | ac334c8c92367b4baf2df4bd52430b95261b962d (diff) | |
Doc: Update HOWTO.md with --mip-level example for full pipeline
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
| -rw-r--r-- | doc/HOWTO.md | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/doc/HOWTO.md b/doc/HOWTO.md index 9003fe1..f89d375 100644 --- a/doc/HOWTO.md +++ b/doc/HOWTO.md @@ -138,12 +138,16 @@ Enhanced CNN with parametric static features (7D input: RGBD + UV + sin encoding ```bash # Train → Export → Build → Validate ./scripts/train_cnn_v2_full.sh + +# With custom mip level for p0-p3 features +./scripts/train_cnn_v2_full.sh --mip-level 1 ``` Config: 100 epochs, 3×3 kernels, 8→4→4 channels, patch-based (harris detector). - Live progress with single-line update - Validates all input images on final epoch - Exports binary weights (storage buffer architecture) +- Mip level: 0 (default, original resolution) **Validation Only** (skip training): ```bash |