Skip OP/ED files by default (--all-files to include)

Real-run evidence: the transformation-emblem false positive (frame 1583
of the OP, 717x857, aspect 0.84) is geometrically face-shaped and
passes every box gate; OP/ED music videos are dominated by exactly that
kind of stylized graphics. Episodes carry the character close-ups a
grounding dataset needs. Verified on the second run: feather storm
(frame 29, area .64) now correctly rejected by the area cap.
This commit is contained in:
2026-10-18 11:07:53 -04:00
parent 89b0f708d7
commit 16ef032611
2 changed files with 22 additions and 5 deletions
+1
View File
@@ -64,6 +64,7 @@ context leaks onto the wrong card:
| `--edge-margin` | 0 | require faces this far inside frame edges; `0` accepts edge-touching faces (original hard-rejected them) |
| `--scene-threshold` | 30.0 | PySceneDetect ContentDetector threshold (same as original) |
| `--imgsz` | 1280 | inference size; model was trained at 1280, `640` is faster at some recall cost |
| `--all-files` | off | also scan OP/ED files. Off by default: music videos are full of stylized graphics (feather storms, transformation emblems) that false-positive as face-shaped; episodes carry the real character close-ups |
| `--preview-dir` | off | also write annotated copies (green boxes) of every saved frame for eyeball QC |
## Notes