dtourolle/DarkRoom
1
0
Fork 0
Code Issues 39 Pull Requests Actions Packages Projects Releases 20 Wiki Activity

Record whole-frame denoise in the spec and the model licences

Browse Source 
denoise.md §14: why the tiles waste half of Best's work, where the any-size
networks run and why only there, why the limit is the card's memory, and
the measurement on _MG_8862 — 2.60 s in 1408 tiles, 1.37 s in two
4160 x 3248 tiles, the outputs within fp16's own spread. models/LICENCE.md
lists the three re-exports.
This commit is contained in:
dtourolle
2026-10-06 23:14:11 -04:00
parent 1e1aa1442b
commit 4b71ef0947
2 changed files with 46 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
models/LICENCE.md
+1
View File
@@ -137,6 +137,7 @@ declined, and the InsightFace grant of D13).
| `denoise/mosaic-best-1408.onnx` | trained in the `darkroom-denoise` repository (2026-10-04, run `final`, 30 000 steps, from the experts of runs `m2` and `edges-100`) | 1,701 of the maintainer's own base-ISO raws and 6,000 synthetic scenes the repository draws itself, with the Canon EOS 6D's measured noise added | the learned demosaic and denoise, Best (FR-DEV-3g) |
| `denoise/mosaic-medium-1408.onnx` | distilled from `final` in the same repository (2026-10-04, run `student-m`, 20 000 steps, from `m2`) | the same | Medium |
| `denoise/mosaic-fast-1408.onnx` | distilled from `final` (2026-10-04, run `student-s`, 30 000 steps, from scratch) | the same | Fast |
| `denoise/mosaic-{best,medium,fast}.onnx` | the three networks above, re-exported with any height and width by `tools/export_whole.py` in the same repository (2026-10-06) from the same checkpoints; identical to the 1408 files at 1408² | the same | the same methods, a whole frame at a time on a GPU (denoise.md §14) |
U-Nets of plain 3×3 convolutions, ReLU, strided and transposed
convolutions and additive skips — no third-party architecture code or