| Age | Commit message (Collapse) | Author |
|---|
|
architecture PNG
- Replace 1×1 pointwise bottleneck with Conv(8→8, 3×3, dilation=2):
effective RF grows from ~13px to ~29px at ¼res (~+1 KB weights)
- Add Sobel edge loss in training (--edge-loss-weight, default 0.1)
- Add FiLM 2-phase training: freeze MLP for warmup epochs then
unfreeze at lr×0.1 (--film-warmup-epochs, default 50)
- Update weight layout: BN 72→584 f16, total 1964→2476 f16 (4952 B)
- Cascade offsets in C++ effect, JS tool, export/gen_test_vectors scripts
- Regenerate test_vectors.h (1238 u32); parity max_err=9.77e-04
- Generate dark-theme U-Net+FiLM architecture PNG (gen_architecture_png.py)
- Replace ASCII art in CNN_V3.md and HOW_TO_CNN.md with PNG embed
handoff(Gemini): bottleneck dilation + Sobel loss + FiLM warmup landed.
Next: run first real training pass (see cnn_v3/docs/HOWTO.md §3).
|
|
- train_cnn_v3.py: --single-sample <dir> implies --full-image + --batch-size 1
- cnn_v3_utils.py: CNNv3Dataset accepts single_sample= kwarg (explicit override)
- HOWTO.md: document --single-sample workflow, fix pack_photo_sample.py usage (--target required)
- HOW_TO_CNN.md: fix GBufferEffect seq input (prev_cnn→source), fix binary name (demo→demo64k), add --resume to flag table, remove stale "pack without target" block
handoff(Gemini): --single-sample <dir> added to train_cnn_v3.py; docs audited and corrected
|
|
- 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`
|
|
Replace raw shadow (ch18) with dif = max(0,dot(normal,KEY_LIGHT))*shadow
across all layers. Channel count stays 20, weight shapes unchanged.
- gbuf_pack.wgsl: t1.z = pack4x8unorm(mip2.g, mip2.b, dif, transp); t1.w = 0u
- gbuf_deferred.wgsl: read dif from unpack4x8unorm(t1.z).z
- gbuf_view.wgsl: revert to 4×5 grid, ch18=dif label, ch19=trns label
- tools/shaders.js: FULL_PACK_SHADER adds oct_decode + computes dif
- cnn_v3_utils.py: assemble_features() computes dif on-the-fly via oct_decode
- docs: CNN_V3.md, HOWTO.md, HOW_TO_CNN.md, GBUF_DIF_MIGRATION.md updated
handoff(Gemini): shadow→dif migration done, ready for first training pass
|
|
- Add WEIGHTS_CNN_V3 and WEIGHTS_CNN_V3_FILM_MLP to workspaces/main/assets.txt
- Add opencv-python and pillow to export_cnn_v3_weights.py uv inline deps
- Update HOW_TO_CNN.md §3 export target → workspaces/main/weights/
- Update HOW_TO_CNN.md §4 weight loading → SafeGetAsset (asset system)
handoff(Gemini): cnn_v3 weight assets registered; export and C++ load path documented
|
|
handoff(Gemini): train_cnn_v3.py now has uv script metadata block
(torch, torchvision, numpy, pillow, opencv-python). HOW_TO_CNN §2
Prerequisites updated with uv quick-start alternative.
|
|
|
|
target.png can have a different resolution than albedo.png in simple
samples; patch slicing into the smaller target produced 0×0 tensors,
crashing torch.stack in the DataLoader collate.
handoff(Gemini): target resized in _load_sample (LANCZOS) + note in HOW_TO_CNN §1c.
|
|
handoff(Gemini): added render + batch-pack example commands at end of section 1b
|
|
blender_export.py:
- Replace broken compositor FileOutput approach with native OPEN_EXR_MULTILAYER
render output; all enabled passes included automatically, no socket wiring needed
- Suppress Fra:/Mem: render spam via os.dup2 fd redirect; per-frame progress
printed to stderr via render_post handler
pack_blender_sample.py:
- get_pass_r: try .R/.X/.Y/.Z/'' suffixes + aliases param for Depth→Z fallback
- combined_rgba loaded once via ("Combined","Image") loop; shared by transp+target
- Remove unused sys import
HOW_TO_CNN.md: update channel table to native EXR naming (Depth.Z, IndexOB.X,
Shadow.X), fix example command, note Shadow defaults to 255 when absent
handoff(Gemini): blender pipeline now produces correct multilayer EXR with all
G-buffer passes; pack script handles native channel naming
|
|
|
|
|
|
Fixes KeyError when blend file uses a non-default view layer name.
Adds --view-layer NAME arg; pass '?' to list available layers.
Defaults to index 0 with a clear error if the name is not found.
handoff(Gemini): blender_export.py view layer selection now robust
|
|
- 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
|
|
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>
|
|
- 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>
|
