diff options
| author | skal <pascal.massimino@gmail.com> | 2026-03-22 16:21:25 +0100 |
|---|---|---|
| committer | skal <pascal.massimino@gmail.com> | 2026-03-22 16:21:25 +0100 |
| commit | 159ca2ca19345515cdfebed9fd88646730492cd2 (patch) | |
| tree | 75f350e4e89003b914e0645e47118f88992d66c0 /cnn_v3/README.md | |
| parent | c8d5c02bae82e506f6bb507c9ed07aeba3a1bb87 (diff) | |
feat(cnn_v3): add G-buffer visualizer + web sample loader (Phase 7)
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).
Diffstat (limited to 'cnn_v3/README.md')
| -rw-r--r-- | cnn_v3/README.md | 15 |
1 files changed, 12 insertions, 3 deletions
diff --git a/cnn_v3/README.md b/cnn_v3/README.md index f161bf4..a844b1b 100644 --- a/cnn_v3/README.md +++ b/cnn_v3/README.md @@ -31,9 +31,18 @@ Add images directly to these directories and commit them. ## Status -**Phase 1 complete.** G-buffer integrated (raster + pack), 35/35 tests pass. -Training infrastructure ready. U-Net WGSL shaders are next. +**Phases 1–7 complete.** 36/36 tests pass. -See `cnn_v3/docs/HOWTO.md` for the practical playbook. +| Phase | Status | +|-------|--------| +| 1 — G-buffer (raster + pack) | ✅ | +| 2 — Training infrastructure | ✅ | +| 3 — WGSL U-Net shaders | ✅ | +| 4 — C++ CNNv3Effect + FiLM | ✅ | +| 5 — Parity validation | ✅ max_err=4.88e-4 | +| 6 — Training script | ✅ train_cnn_v3.py | +| 7 — Validation tools | ✅ GBufViewEffect + web sample loader | + +See `cnn_v3/docs/HOWTO.md` for the practical playbook (§9 covers validation tools). See `cnn_v3/docs/CNN_V3.md` for full design. See `cnn_v2/` for reference implementation. |