Freeze aerial warmup across training loop

2026-07-29 16:27:30 +02:00
parent b393d9f65d
commit 18387448de
5 changed files with 46 additions and 0 deletions
@@ -978,6 +978,7 @@ This file now starts with the current implementation status. Older preparation/b
 - [x] Bind v37 completion to a one-shot JSON command that enters calibration-first evaluation and up to 20 automatic failure-driven CUDA iterations with the frozen aerial augmentation contract.
 - [x] Complete v37 by early stopping at epoch 23, reject its best epoch-5 checkpoint calibration-first, and start closed-loop iteration 2 from checksummed failure-driven sampling.
 - [x] Make orchestrator patience explicit and retain the frozen value `18` in every subsequent CUDA iteration.
+- [x] Preserve v37 warmup and aerial HSV augmentation in every loop iteration; archive and invalidate the pre-epoch-2 run that exposed generic Ultralytics warmup drift.
 - [x] Evaluate the completed v36 YOLO11x checkpoint calibration-first on the rotated v30 holdouts; reject it before opening test/background because the regional calibration gate failed.
 - [ ] Finish and assess the leak-free v37 YOLO11x failure-driven CUDA iteration; open test/background evidence only if every calibration gate passes.