From 6fa9ccf86b0bbefb48cefae19d4162115a3d63d3 Mon Sep 17 00:00:00 2001 From: skal Date: Fri, 13 Feb 2026 23:17:42 +0100 Subject: CNN v2: Alpha channel depth handling and layer visualization Training changes: - Changed p3 default depth from 0.0 to 1.0 (far plane semantics) - Extract depth from target alpha channel in both datasets - Consistent alpha-as-depth across training/validation Test tool enhancements (cnn_test): - Added load_depth_from_alpha() for R32Float depth texture - Fixed bind group layout for UnfilterableFloat sampling - Added --save-intermediates with per-channel grayscale composites - Each layer saved as 4x wide PNG (p0-p3 stacked horizontally) - Global layers_composite.png for vertical layer stack overview Investigation notes: - Static features p4-p7 ARE computed and bound correctly - Sin_20_y pattern visibility difference between tools under investigation - Binary weights timestamp (Feb 13 20:36) vs HTML tool (Feb 13 22:12) - Next: Update HTML tool with canonical binary weights handoff(Claude): HTML tool weights update pending - base64 encoded canonical weights ready in /tmp/weights_b64.txt for line 392 replacement. Co-Authored-By: Claude Sonnet 4.5 --- layer_0.png | Bin 0 -> 42621 bytes 1 file changed, 0 insertions(+), 0 deletions(-) create mode 100644 layer_0.png (limited to 'layer_0.png') diff --git a/layer_0.png b/layer_0.png new file mode 100644 index 0000000..91d3786 Binary files /dev/null and b/layer_0.png differ -- cgit v1.2.3