diff --git a/pipeline/run_pipeline.sh b/pipeline/run_pipeline.sh index 207bd7a..d64e867 100755 --- a/pipeline/run_pipeline.sh +++ b/pipeline/run_pipeline.sh @@ -42,6 +42,13 @@ echo "--- Stage 04: frame extract ---" | tee -a "${RUN_LOG_DIR}/run.log" python3 "${PIPELINE_DIR}/04_frame_extract.py" --mission "${MISSION}" \ 2>&1 | tee -a "${RUN_LOG_DIR}/stage04.log" "${RUN_LOG_DIR}/run.log" + +# Stage 04b: trim hors-eau head/tail (no-regression guard built into script) +echo "" | tee -a "${RUN_LOG_DIR}/run.log" +echo "--- Stage 04b: trim hors-eau head/tail ---" | tee -a "${RUN_LOG_DIR}/run.log" +python3 "${PIPELINE_DIR}/04b_trim_water.py" --mission "${MISSION}" \ + 2>&1 | tee -a "${RUN_LOG_DIR}/stage04b.log" "${RUN_LOG_DIR}/run.log" + # Stage 05: inference (sequential, one segment at a time) echo "" | tee -a "${RUN_LOG_DIR}/run.log" echo "--- Stage 05: inference ---" | tee -a "${RUN_LOG_DIR}/run.log" diff --git a/pipeline/stages/04b_trim_water.py b/pipeline/stages/04b_trim_water.py index ebdb6d3..4c57134 100644 --- a/pipeline/stages/04b_trim_water.py +++ b/pipeline/stages/04b_trim_water.py @@ -289,6 +289,18 @@ def process_segment(mission_name: str, auv_id: str, segment: str, # Re-QC if not dry-run and something was trimmed (or always to keep metrics fresh) after_agg = None if not dry_run and (head > 0 or tail > 0): + # No-regression guard: compute expected post-trim pct before deleting frames + remaining_paths_check = sorted(frames_dir.glob("frame_*.jpg"))[head: len(before_paths) - tail if tail else None] + sampled_check = remaining_paths_check[::max(1, QC_SAMPLE_RATE)] + pf_check = [s for s in (score_image_file(f) for f in sampled_check) if s is not None] + if pf_check: + after_check = qc_aggregate(pf_check).get("bottom_visible_pct", 0) + before_pct = result.get("before_bottom_pct") or 0 + if after_check < before_pct: + result["skipped"] = True + result["reason"] = f"no_regression_guard: {before_pct}%→{after_check}% (trim would worsen)" + print(f" [04b] SKIP {auv_id}/{segment}: trim would worsen {before_pct}%→{after_check}%") + return result after_agg = qc_segment(frames_dir) elif dry_run: # In dry-run, don't touch qc.json; compute aggregate from remaining slice in-memory diff --git a/pipeline/stages/05_inference.py b/pipeline/stages/05_inference.py index 274a1ab..659d898 100644 --- a/pipeline/stages/05_inference.py +++ b/pipeline/stages/05_inference.py @@ -158,7 +158,7 @@ def run_inference(frames_dir: Path, worker_key: str, mission_name: str, f"--overlap_size 16 " f"--save_ply {ply_remote} " f"--save_poses {npz_remote} " - f"--use_sdpa " + f"--use_sdpa " f"--offload_to_cpu " f"--ply_conf_threshold 1.5 " f"2>&1" )