From f72f404e755149e80350dc6eb34015d5e7630d44 Mon Sep 17 00:00:00 2001 From: skal Date: Sat, 14 Feb 2026 01:37:50 +0100 Subject: Document CNN v2 training pipeline improvements - HOWTO.md: Document always-save-checkpoint behavior and --quiet flag - COMPLETED.md: Add milestone entry for Feb 14 CNN v2 fixes - Details: checkpoint saving, num_layers derivation, output streamlining Co-Authored-By: Claude Sonnet 4.5 --- doc/HOWTO.md | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'doc/HOWTO.md') diff --git a/doc/HOWTO.md b/doc/HOWTO.md index c98f6ee..506bf0a 100644 --- a/doc/HOWTO.md +++ b/doc/HOWTO.md @@ -166,8 +166,11 @@ Enhanced CNN with parametric static features (7D input: RGBD + UV + sin encoding **Defaults:** 200 epochs, 3×3 kernels, 8→4→4 channels, batch-size 16, patch-based (8×8, harris detector). - Live progress with single-line update +- Always saves final checkpoint (regardless of --checkpoint-every interval) +- When multiple kernel sizes provided (e.g., 3,5,3), num_layers derived from list length - Validates all input images on final epoch - Exports binary weights (storage buffer architecture) +- Streamlined output: single-line export summary, compact validation - All parameters configurable via command-line **Validation Only** (skip training): @@ -207,12 +210,19 @@ Enhanced CNN with parametric static features (7D input: RGBD + UV + sin encoding **Export Binary Weights:** ```bash +# Verbose output (shows all layer details) ./training/export_cnn_v2_weights.py checkpoints/checkpoint_epoch_100.pth \ --output-weights workspaces/main/cnn_v2_weights.bin + +# Quiet mode (single-line summary) +./training/export_cnn_v2_weights.py checkpoints/checkpoint_epoch_100.pth \ + --output-weights workspaces/main/cnn_v2_weights.bin \ + --quiet ``` Generates binary format: header + layer info + f16 weights (~3.2 KB for 3-layer model). Storage buffer architecture allows dynamic layer count. +Use `--quiet` for streamlined output in scripts (used automatically by train_cnn_v2_full.sh). **TODO:** 8-bit quantization for 2× size reduction (~1.6 KB). Requires quantization-aware training (QAT). -- cgit v1.2.3