ffc30d7377
- Fix swift_pose/swift_ocr Y-flip bugs (BUG-003~006) - Add heuristic_scene module + post-processing trigger (replaces Places365) - YOLOv5nu → YOLOv8s CoreML (+33% detections, +390% scene indicators) - Per-table SQL export (split 4.7GB single file → 478MB max per table) - Version/build check in deploy.sh (compare /health vs file_info.json) - Add file_uuid column to identities table + backfill - Identity pre-clean step in deploy (avoids UNIQUE conflicts on re-deploy) - Stranger_xxx naming fix with UUID context - Add DETECTOR_REGISTRY.md (25 detectors), DETECTOR_SELECTION_SOP.md - Update SPATIAL_COORDINATE_REGISTRY.md (P layer, 6-layer architecture) - New IDENTITY_LIFECYCLE.md - M4 response docs for deploy_script_fix and 111614 test report
Identity Clustering 實驗記錄區
每個實驗獨立運行，結果完整保留，用於後續分析比較。
目錄結構
experiments/identity_clustering/
├── README.md # 本文件
├── configs/ # 實驗配置
│ └── exp_{id}.json # 每個實驗的參數設定
├── results/ # 實驗結果
│ └── exp_{id}/
│ ├── clusters.json # 分群結果
│ ├── labels.json # 標註結果（TMDb/Speaker）
│ ├── metrics.json # 評估指標
│ └── summary.txt # 摘要報告
├── reports/ # 比較分析報告
│ └── comparison_{date}.md # 跨實驗比較
└── runner.py # 實驗執行器
實驗設計
每個實驗包含以下維度的組合：
| 維度 | 選項 |
|---|---|
| Trace filter | none / min_frames=30 / min_frames=60 |
| Centroid | mean / median / best_confidence |
| Clustering | cosine_threshold / DBSCAN / Agglomerative |
| Threshold | fixed=0.85 / adaptive(pose) / auto |
| TMDb | enabled / disabled |
| Speaker verify | ✅ 標準工序（所有實驗強制） |
當前輸入數據
- file_uuid:
1a04db97be5fa12bd77369831dc141fd - 6182 detections, 2347 traces, 512D embeddings
- 10 speakers (ASRX), 57 YOLO objects
- TMDb identities: available (Charade 1963 cast)