| Age | Commit message (Collapse) | Author |
|---|
|
Double encoder capacity: enc0 4→8ch, enc1 8→16ch, bottleneck 16→16ch,
dec1 32→8ch, dec0 16→4ch. Total weights 2476→7828 f16 (~15.3 KB).
FiLM MLP output 40→72 params (L1: 16×40→16×72).
16-ch textures split into _lo/_hi rgba32uint pairs (enc1, bottleneck).
enc0 and dec1 textures changed from rgba16float to rgba32uint (8ch).
GBUF_RGBA32UINT node gains CopySrc for parity test readback.
- WGSL shaders: all 5 passes rewritten for new channel counts
- C++ CNNv3Effect: new weight offsets/sizes, 8ch uniform structs
- Web tool (shaders.js + tester.js): matching texture formats and bindings
- Parity test: readback_rgba32uint_8ch helper, updated vector counts
- Training scripts: default enc_channels=[8,16], updated docstrings
- Docs + architecture PNG regenerated
handoff(Gemini): CNN v3 [8,16] upgrade complete. All code, tests, web
tool, training scripts, and docs updated. Next: run training pass.
|
|
- Layer viz button was labeled 'Output' instead of 'Dec0'
- BN parseWeights cnt was stale (old 1×1 conv size); now 8×8×9+8=584
handoff(Gemini): web tool only, no C++ or shader changes
|
|
- cnn_v3/tools/weights.js: new file — base64-encoded cnn_v3_weights.bin +
cnn_v3_film_mlp.bin; loaded at startup so the tool works without dropping files
- tester.js: preload() falls back to embedded weights.js constants when fetch
fails; logs "Loaded embedded" vs "Preloaded" to distinguish the two paths
- index.html: load weights.js before tester.js
- export_cnn_v3_weights.py: add --html / --html-output flags that call
update_weights_js() to regenerate weights.js after a training run
- HOW_TO_CNN.md: update pipeline diagram, §3 export commands, §7 HTML tool
section (file table, workflow, weights.js description), Appendix A
handoff(Gemini): weights.js now the canonical source for HTML tool defaults;
regenerate with `uv run export_cnn_v3_weights.py <ckpt> --output ... --html`
|
|
|
|
|
|
|
|
measure)
|
|
|
|
|
|
|
|
WebGPU auto-reflects the BGL from the shader; a declared-but-unused sampler
binding is omitted from the layout, causing CreateBindGroup to reject it.
Removed binding 6 (sampler) entirely — all reads use textureLoad(). Renumbered
f0/f1 from 7/8 to 6/7 to match.
|
|
C++ GBufViewEffect: renders all 20 feature channels from feat_tex0/feat_tex1
in a 4×5 tiled grid. Custom BGL with WGPUTextureSampleType_Uint; bind group
rebuilt per frame via wgpuRenderPipelineGetBindGroupLayout.
Web tool: "Load sample directory" button — webkitdirectory picker, FULL_PACK_SHADER
compute (matches gbuf_pack.wgsl packing), runFromFeat() skips photo-pack step,
computePSNR() readback + comparison vs target.png side-by-side.
36/36 tests pass. Docs updated: HOWTO.md §9, README, PROJECT_CONTEXT, TODO,
COMPLETED.
handoff(Gemini): CNN v3 Phase 7 done. Next: run train_cnn_v3.py (see HOWTO §3).
|
|
- Bind document.getElementById in filmParams() to fix 'Illegal invocation' error
- Add preload() that auto-fetches cnn_v3_weights.bin + cnn_v3_film_mlp.bin from
workspaces/main/weights/ on init; skips silently if files not found
- Add '↺ Reload from workspace weights/' button for manual re-fetch
handoff(Gemini): cnn_v3 web tool fixed; serve from repo root via http.server
|
|
3-file tool, 939 lines total. Implements full U-Net+FiLM inference in
the browser: Pack→Enc0→Enc1→Bottleneck→Dec1→Dec0 compute passes,
layer visualisation (Feat/Enc0/Enc1/BN/Dec1/Output), FiLM MLP sliders,
drag-drop weights + image/video, Save PNG, diff/blend view modes.
HOW_TO_CNN.md §7 updated to reflect tool is implemented.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
