Suppress duplicate YOLO tile detections

scripts/README.md

@@ -226,6 +226,9 @@ logs plus `calibration_summary.json` under
 `CALIBRATION_OUTPUT_DIR` is set. This is a calibration/benchmarking tool only:
 it does not seed demo data, enable fixture detections, fetch external data or
 download model weights.
+Per-threshold summaries include persisted detection count, raw candidate count
+before GeoIntel duplicate suppression, suppressed duplicate count and the
+configured duplicate IoU threshold.
 
 Run a broader model/tile/threshold quality matrix when multiple local model
 assets or tile settings need to be compared:

scripts/run_detection_calibration_sweep.sh

@@ -98,6 +98,7 @@ for threshold in ${thresholds_normalized}; do
   threshold_label="$(printf '%s' "${threshold}" | tr '.-' 'pm')"
   run_log="${CALIBRATION_OUTPUT_DIR}/threshold_${threshold_label}.log"
   quality_response="${CALIBRATION_OUTPUT_DIR}/threshold_${threshold_label}_quality_checks.json"
+  detection_run_response="${CALIBRATION_OUTPUT_DIR}/threshold_${threshold_label}_detection_run.json"
   run_summary="${CALIBRATION_OUTPUT_DIR}/threshold_${threshold_label}_summary.json"
 
   echo "-- Threshold ${threshold} (${run_index}) --"
@@ -121,9 +122,11 @@ for threshold in ${thresholds_normalized}; do
   fi
 
   curl -fsS "${BASE_URL%/}/api/v1/projects/${project_id}/quality-checks?limit=200" > "${quality_response}"
+  curl -fsS "${BASE_URL%/}/api/v1/detection/runs/${analysis_run_id}" > "${detection_run_response}"
 
   "${PYTHON_BIN}" - \
     "${quality_response}" \
+    "${detection_run_response}" \
     "${run_summary}" \
     "${threshold}" \
     "${project_id}" \
@@ -134,11 +137,17 @@ for threshold in ${thresholds_normalized}; do
 import json
 import sys
 
-quality_path, output_path, threshold, project_id, analysis_run_id, quality_check_id, detection_count, run_log = sys.argv[1:9]
+quality_path, detection_run_path, output_path, threshold, project_id, analysis_run_id, quality_check_id, detection_count, run_log = sys.argv[1:10]
 with open(quality_path, "r", encoding="utf-8") as handle:
     payload = json.load(handle)
 if "data" not in payload:
     raise SystemExit("Quality-check list is not a canonical GeoIntel data envelope")
+with open(detection_run_path, "r", encoding="utf-8") as handle:
+    detection_run_payload = json.load(handle)
+if "data" not in detection_run_payload:
+    raise SystemExit("Detection run detail is not a canonical GeoIntel data envelope")
+detection_run = detection_run_payload["data"]
+run_result = detection_run.get("result_json") or {}
 items = payload["data"].get("items") or []
 quality_check = next((item for item in items if str(item.get("id")) == quality_check_id), None)
 if quality_check is None:
@@ -157,6 +166,9 @@ summary = {
     "detection_count": int(detection_count),
     "quality_status": quality_check.get("status"),
     "quality_score": quality_check.get("score"),
+    "raw_detection_count": run_result.get("raw_detection_count", int(detection_count)),
+    "suppressed_detection_count": run_result.get("suppressed_detection_count", 0),
+    "duplicate_iou_threshold": run_result.get("duplicate_iou_threshold"),
     "precision": metrics.get("precision"),
     "recall": metrics.get("recall"),
     "f1_score": metrics.get("f1_score", metrics.get("f1")),
@@ -169,10 +181,12 @@ summary = {
 with open(output_path, "w", encoding="utf-8") as handle:
     json.dump(summary, handle, indent=2, sort_keys=True)
 print(
-    "threshold={threshold} detections={detections} score={score} "
+    "threshold={threshold} detections={detections} raw={raw} suppressed={suppressed} score={score} "
     "precision={precision} recall={recall} f1={f1} matches={matches} fp={fp} fn={fn}".format(
         threshold=summary["threshold"],
         detections=summary["detection_count"],
+        raw=summary["raw_detection_count"],
+        suppressed=summary["suppressed_detection_count"],
         score=summary["quality_score"],
         precision=summary["precision"],
         recall=summary["recall"],
@@ -217,10 +231,10 @@ with open(summary_path, "w", encoding="utf-8") as handle:
 
 print("")
 print("Detection calibration summary")
-print("threshold\tdetections\tscore\tprecision\trecall\tf1\tmatches\tfp\tfn")
+print("threshold\tdetections\traw\tsuppressed\tscore\tprecision\trecall\tf1\tmatches\tfp\tfn")
 for item in items:
     print(
-        "{threshold:.2f}\t{detection_count}\t{quality_score}\t{precision}\t{recall}\t{f1_score}\t{matches}\t{false_positives}\t{false_negatives}".format(
+        "{threshold:.2f}\t{detection_count}\t{raw_detection_count}\t{suppressed_detection_count}\t{quality_score}\t{precision}\t{recall}\t{f1_score}\t{matches}\t{false_positives}\t{false_negatives}".format(
             **item
         )
     )

scripts/run_detection_quality_matrix.sh

@@ -168,6 +168,7 @@ while IFS=$'\t' read -r model_request tile_size tile_overlap threshold run_label
   run_index=$((run_index + 1))
   run_log="${QUALITY_OUTPUT_DIR}/${run_label}.log"
   quality_response="${QUALITY_OUTPUT_DIR}/${run_label}_quality_checks.json"
+  detection_run_response="${QUALITY_OUTPUT_DIR}/${run_label}_detection_run.json"
   run_summary="${QUALITY_OUTPUT_DIR}/${run_label}_summary.json"
   model_env="${model_request}"
   if [ "${model_request}" = "__active__" ]; then
@@ -203,9 +204,11 @@ while IFS=$'\t' read -r model_request tile_size tile_overlap threshold run_label
   fi
 
   curl -fsS "${BASE_URL%/}/api/v1/projects/${project_id}/quality-checks?limit=200" > "${quality_response}"
+  curl -fsS "${BASE_URL%/}/api/v1/detection/runs/${analysis_run_id}" > "${detection_run_response}"
 
   "${PYTHON_BIN}" - \
     "${quality_response}" \
+    "${detection_run_response}" \
     "${run_summary}" \
     "${model_request}" \
     "${selected_model_asset_id}" \
@@ -226,6 +229,7 @@ import sys
 
 (
     quality_path,
+    detection_run_path,
     output_path,
     model_request,
     selected_model_asset_id,
@@ -241,12 +245,18 @@ import sys
     detection_count,
     export_id,
     run_log,
-) = sys.argv[1:17]
+) = sys.argv[1:18]
 
 with open(quality_path, "r", encoding="utf-8") as handle:
     payload = json.load(handle)
 if "data" not in payload:
     raise SystemExit("Quality-check list is not a canonical GeoIntel data envelope")
+with open(detection_run_path, "r", encoding="utf-8") as handle:
+    detection_run_payload = json.load(handle)
+if "data" not in detection_run_payload:
+    raise SystemExit("Detection run detail is not a canonical GeoIntel data envelope")
+detection_run = detection_run_payload["data"]
+run_result = detection_run.get("result_json") or {}
 items = payload["data"].get("items") or []
 quality_check = next((item for item in items if str(item.get("id")) == quality_check_id), None)
 if quality_check is None:
@@ -270,6 +280,9 @@ summary = {
     "analysis_run_id": analysis_run_id,
     "quality_check_id": quality_check_id,
     "detection_count": int(detection_count),
+    "raw_detection_count": run_result.get("raw_detection_count", int(detection_count)),
+    "suppressed_detection_count": run_result.get("suppressed_detection_count", 0),
+    "duplicate_iou_threshold": run_result.get("duplicate_iou_threshold"),
     "quality_status": quality_check.get("status"),
     "quality_score": quality_check.get("score"),
     "precision": metrics.get("precision"),
@@ -285,13 +298,15 @@ summary = {
 with open(output_path, "w", encoding="utf-8") as handle:
     json.dump(summary, handle, indent=2, sort_keys=True)
 print(
-    "model={model} tile={tile} overlap={overlap} threshold={threshold} detections={detections} "
+    "model={model} tile={tile} overlap={overlap} threshold={threshold} detections={detections} raw={raw} suppressed={suppressed} "
     "score={score} precision={precision} recall={recall} f1={f1} matches={matches} fp={fp} fn={fn}".format(
         model=summary["model_asset_id"],
         tile=summary["tile_size"],
         overlap=summary["tile_overlap"],
         threshold=summary["threshold"],
         detections=summary["detection_count"],
+        raw=summary["raw_detection_count"],
+        suppressed=summary["suppressed_detection_count"],
         score=summary["quality_score"],
         precision=summary["precision"],
         recall=summary["recall"],
@@ -346,10 +361,10 @@ with open(summary_path, "w", encoding="utf-8") as handle:
 
 print("")
 print("Detection quality matrix summary")
-print("model\ttile\toverlap\tthreshold\tdetections\tscore\tprecision\trecall\tf1\tmatches\tfp\tfn")
+print("model\ttile\toverlap\tthreshold\tdetections\traw\tsuppressed\tscore\tprecision\trecall\tf1\tmatches\tfp\tfn")
 for item in items:
     print(
-        "{model_asset_id}\t{tile_size}\t{tile_overlap}\t{threshold:.2f}\t{detection_count}\t{quality_score}\t{precision}\t{recall}\t{f1_score}\t{matches}\t{false_positives}\t{false_negatives}".format(
+        "{model_asset_id}\t{tile_size}\t{tile_overlap}\t{threshold:.2f}\t{detection_count}\t{raw_detection_count}\t{suppressed_detection_count}\t{quality_score}\t{precision}\t{recall}\t{f1_score}\t{matches}\t{false_positives}\t{false_negatives}".format(
             **item
         )
     )

scripts/run_multi_sample_detection_quality_matrix.sh

@@ -205,10 +205,10 @@ summary_path.write_text(json.dumps(summary, indent=2, sort_keys=True), encoding=
 
 print("")
 print("Multi-sample detection quality summary")
-print("sample\tmodel\ttile\toverlap\tthreshold\tdetections\tscore\tprecision\trecall\tf1\tmatches\tfp\tfn")
+print("sample\tmodel\ttile\toverlap\tthreshold\tdetections\traw\tsuppressed\tscore\tprecision\trecall\tf1\tmatches\tfp\tfn")
 for item in flat_items:
     print(
-        "{sample_slug}\t{model_asset_id}\t{tile_size}\t{tile_overlap}\t{threshold:.2f}\t{detection_count}\t{quality_score}\t{precision}\t{recall}\t{f1_score}\t{matches}\t{false_positives}\t{false_negatives}".format(
+        "{sample_slug}\t{model_asset_id}\t{tile_size}\t{tile_overlap}\t{threshold:.2f}\t{detection_count}\t{raw_detection_count}\t{suppressed_detection_count}\t{quality_score}\t{precision}\t{recall}\t{f1_score}\t{matches}\t{false_positives}\t{false_negatives}".format(
             **item
         )
     )