Prepare unique hard-negative training dataset

2026-07-09 02:20:49 +02:00
parent 54e6ad888e
commit 20c942df50
6 changed files with 39 additions and 5 deletions
@@ -354,6 +354,13 @@ Current Tower audit status:
  background AOIs before training another hard-negative-balanced candidate.
 - Regenerate `operator_samples_manifest.json` after pulling Sprint 147+ so the
  expanded unique background AOI set is available for the next tile export.
+- `yolo-building-tile-uniquehardneg160`: clean expanded-background baseline;
+  576 tiles, 346 positive, 230 negative, 11,757 labels, 0 invalid labels and
+  0 repeated background negatives in the first Tower audit.
+
+After rebuilding the all-in-one image, the operator scripts are available inside
+the container at `/app/scripts/...`. Before rebuilding, use the host checkout or
+temporarily copy scripts into the running container for one-off data prep.

 For hard-negative-balanced experiments, repeat only train-split negative tiles
 from samples marked `sample_role=background_candidate`: