summaryrefslogtreecommitdiff
path: root/cnn_v3
AgeCommit message (Collapse)Author
11 hoursfeat(cnn_v3): gen_sample tool + 7 simple training samplesskal
- pack_photo_sample.py: --target now required (no albedo fallback) - gen_sample.py: bash wrapper with positional args (input target output_dir) - input/photo7.jpg: copy of photo2 (second style target) - target_1: photo2_1_out→photo2_out, photo2_2_out→photo7_out - dataset/simple/sample_001..007: 7 packed photo/target pairs handoff(Gemini): training data ready; next step is train_cnn_v3.py run
11 hoursfeat(cnn_v3): gen_sample tool + 7 simple training samplesskal
- pack_photo_sample.py: --target now required (no albedo fallback) - gen_sample: bash wrapper with positional args (input target output_dir) - input/photo7.jpg: copy of photo2 (second style target) - target_1: photo2_1_out→photo2_out, photo2_2_out→photo7_out - dataset/simple/sample_001..007: 7 packed photo/target pairs handoff(Gemini): training data ready; next step is train_cnn_v3.py run
28 hoursrefactor(cnn_v3): code review — comments, simplifications, test fixskal
C++: - cnn_v3_effect.cc: fix declare_nodes comment (output node declared by caller) - cnn_v3_effect.cc: add TODO(phase-7) marker for FiLM MLP replacement WGSL: - cnn_v3_bottleneck.wgsl: consolidate _pad fields onto one line, explain why array<u32,3> is invalid in uniform address space - cnn_v3_enc0.wgsl: fix "12xu8" → "12ch u8norm" in header comment - cnn_v3_dec0.wgsl: clarify parity note (sigmoid after FiLM+ReLU, not raw conv) - cnn_v3_common.wgsl: clarify unpack_8ch pack layout (low/high 16 bits) Python: - cnn_v3_utils.py: replace PIL-based _upsample_nearest (uint8 round-trip) with pure numpy index arithmetic; rename _resize_rgb → _resize_img (handles any channel count); add comment on normal zero-pad workaround - export_cnn_v3_weights.py: add cross-ref to cnn_v3_effect.cc constants; clarify weight count comments with Conv notation Test: - test_cnn_v3_parity.cc: enc0/dec1 layer failures now return 0 (were print-only) handoff(Gemini): CNN v3 review complete, 36/36 tests passing.
31 hoursfeat(cnn_v3): HTML WebGPU tool (index.html + shaders.js + tester.js)skal
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>
32 hoursfeat(cnn_v3): export script + HOW_TO_CNN.md playbookskal
- export_cnn_v3_weights.py: .pth → cnn_v3_weights.bin (f16 packed u32) + cnn_v3_film_mlp.bin (f32) - HOW_TO_CNN.md: full pipeline playbook (data collection, training, export, C++ wiring, parity, HTML tool) - TODO.md: mark export script done Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
32 hoursfeat(cnn_v3): Phase 6 — training script (train_cnn_v3.py + cnn_v3_utils.py)skal
- train_cnn_v3.py: CNNv3 U-Net+FiLM model, training loop, CLI - cnn_v3_utils.py: image I/O, pyrdown, depth_gradient, assemble_features, apply_channel_dropout, detect_salient_points, CNNv3Dataset - Patch-based training (default 64×64) with salient-point extraction (harris/shi-tomasi/fast/gradient/random detectors, pre-cached at init) - Channel dropout for geometric/context/temporal channels - Random FiLM conditioning per sample for joint MLP+U-Net training - docs: HOWTO.md §3 updated with commands and flag reference - TODO.md: Phase 6 marked done, export script noted as next step Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
32 hoursdocs(cnn_v3): update CNN_V3.md + HOWTO.md to reflect Phases 1-5 completeskal
- CNN_V3.md: status line, architecture channel counts (8/16→4/8), FiLM MLP output count (96→40 params), size budget table (real implemented values) - HOWTO.md: Phase status table (5→done, add phase 6 training TODO), sections 3-5 rewritten to reflect what exists vs what is still planned
32 hoursfeat(cnn_v3): Phase 5 complete — parity validation passing (36/36 tests)skal
- Add test_cnn_v3_parity.cc: zero_weights + random_weights tests - Add gen_test_vectors.py: PyTorch reference implementation for enc0/enc1/bn/dec1/dec0 - Add test_vectors.h: generated C header with enc0, dec1, output expected values - Fix declare_nodes(): intermediate textures at fractional resolutions (W/2, W/4) using new NodeRegistry::default_width()/default_height() getters - Add layer-by-layer readback (enc0, dec1) for regression coverage - Final parity: enc0 max_err=1.95e-3, dec1 max_err=1.95e-3, out max_err=4.88e-4 handoff(Claude): CNN v3 parity done. Next: train_cnn_v3.py (FiLM MLP training).
33 hoursfeat(cnn_v3): Phase 4 complete — CNNv3Effect C++ + FiLM uniform uploadskal
- cnn_v3/src/cnn_v3_effect.{h,cc}: full Effect subclass with 5 compute passes (enc0→enc1→bottleneck→dec1→dec0), shared weights storage buffer, per-pass uniform buffers, set_film_params() API - Fixed WGSL/C++ struct alignment: vec3u has align=16, so CnnV3Params4ch is 64 bytes and CnnV3ParamsEnc1 is 96 bytes (not 48/80) - Weight offsets computed as explicit formulas (e.g. 20*4*9+4) for clarity - Registered in CMake, shaders.h/cc, demo_effects.h, test_demo_effects.cc - 35/35 tests pass handoff(Gemini): CNN v3 Phase 5 next — parity validation (Python ref vs WGSL)
33 hoursfeat(cnn_v3): Phase 3 complete — WGSL U-Net inference shadersskal
5 compute shaders + cnn_v3/common snippet: enc0: Conv(20→4,3×3) + FiLM + ReLU full-res enc1: AvgPool + Conv(4→8,3×3) + FiLM + ReLU half-res bottleneck: AvgPool + Conv(8→8,1×1) + ReLU quarter-res dec1: NearestUp + cat(enc1) + Conv(16→4) + FiLM half-res dec0: NearestUp + cat(enc0) + Conv(8→4) + FiLM + Sigmoid full-res Parity rules: zero-pad conv, AvgPool down, NearestUp, FiLM after conv+bias, skip=concat, OIHW weights+bias layout. Matches PyTorch train_cnn_v3.py forward() exactly. Registered in workspaces/main/assets.txt + src/effects/shaders.cc. Weight layout + Params struct documented in cnn_v3/docs/HOWTO.md §7. Next: Phase 4 — C++ CNNv3Effect + FiLM uniform upload. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2 daysfeat(cnn_v3): Phase 1 complete - GBufferEffect integrated + HOWTO playbookskal
- Wire GBufferEffect into demo build: assets.txt, DemoSourceLists.cmake, demo_effects.h, shaders.h/cc. ShaderComposer::Compose() applied to gbuf_raster.wgsl (resolves #include "common_uniforms"). - Add GBufferEffect construction test. 35/35 passing. - Write cnn_v3/docs/HOWTO.md: G-buffer wiring, training data prep, training plan, per-pixel validation workflow, phase status table, troubleshooting guide. - Add project hooks: remind to update HOWTO.md on cnn_v3/ edits; warn on direct str_view(*_wgsl) usage bypassing ShaderComposer. - Update PROJECT_CONTEXT.md and TODO.md: Phase 1 done, Phase 3 (WGSL U-Net shaders) is next active. handoff(Gemini): CNN v3 Phase 3 is next - WGSL enc/dec/bottleneck/FiLM shaders in cnn_v3/shaders/. See cnn_v3/docs/CNN_V3.md Architecture section and cnn_v3/docs/HOWTO.md section 3 for spec. GBufferEffect outputs feat_tex0 + feat_tex1 (rgba32uint, 20ch, 32 bytes/pixel). C++ CNNv3Effect (Phase 4) takes those as input nodes.
2 daysfeat(cnn_v3): G-buffer phase 1 + training infrastructureskal
G-buffer (Phase 1): - Add NodeTypes GBUF_ALBEDO/DEPTH32/R8/RGBA32UINT to NodeRegistry - GBufferEffect: MRT raster pass (albedo+normal_mat+depth) + pack compute - Shaders: gbuf_raster.wgsl (MRT), gbuf_pack.wgsl (feature packing, 32B/px) - Shadow/SDF passes stubbed (placeholder textures), CMake integration deferred Training infrastructure (Phase 2): - blender_export.py: headless EXR export with all G-buffer render passes - pack_blender_sample.py: EXR → per-channel PNGs (oct-normals, 1/z depth) - pack_photo_sample.py: photo → zero-filled G-buffer sample layout handoff(Gemini): G-buffer phases 3-5 remain (U-Net shaders, CNNv3Effect, parity)
3 daysdocs(cnn_v3): full design doc — U-Net + FiLM architecture planskal
- CNN_V3.md: complete design document - U-Net enc_channels=[4,8], ~5 KB f16 weights - FiLM conditioning (5D → γ/β per level, CPU-side MLP) - 20-channel feature buffer, 32 bytes/pixel: two rgba32uint textures - feat_tex0: albedo.rgb, normal.xy, depth, depth_grad.xy (f16) - feat_tex1: mat_id, prev.rgb, mip1.rgb, mip2.rgb, shadow, transp (u8) - 4-pass G-buffer: raster MRT + SDF compute + lighting + pack - Per-pixel parity framework: PyTorch / HTML WebGPU / C++ WebGPU (≤1/255) - Training pipelines: Blender full G-buffer + photo-only (channel dropout) - train_cnn_v3_full.sh spec (modelled on v2 script) - HTML tool adaptation plan from cnn_v2/tools/cnn_v2_test/index.html - Binary format v3 header spec - 8-phase ordered implementation checklist - TODO.md: add CNN v3 U-Net+FiLM future task with phases - cnn_v3/README.md: update status to design phase handoff(Gemini): CNN v3 design complete. Phase 0 (stub G-buffer) unblocks all other phases — one compute shader writing feat_tex0+feat_tex1 with synthetic values from the current framebuffer. See cnn_v3/docs/CNN_V3.md Implementation Checklist.
2026-03-05add training photosskal
2026-02-27remove old files, add new training setskal
2026-02-15feat(cnn): add CNN v3 directory structure with training dataskal
Initialize CNN v3 subdirectory with training pipeline layout: - docs/, scripts/, shaders/, src/, tools/, weights/ for organization - training/input/ with sample images - training/target_1/, target_2/ for multi-style training - README.md documenting structure Training images tracked in repo for easy collaboration. Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
generated by cgit v1.2.3 (git 2.51.0) at 2026-03-22 17:06:16 +0000