Files
geointel/artifacts/evidence/accuracy/model-training/20260809-v67-training-decision.json
T
Jens 7f90f9dde4
GeoIntel release gates / Compile, test, contracts and builds (push) Canceled after 0s
GeoIntel release gates / Python and npm vulnerability policy (push) Canceled after 0s
GeoIntel release gates / GIS image, SBOM and container scan (push) Canceled after 0s
Record governed visual review and GPU training decision
2026-08-09 12:01:17 +02:00

52 lines
1.9 KiB
JSON

{
"schema_version": 1,
"generated_at": "2026-08-09T10:01:00Z",
"run_id": "building-kempen-v67-ai-assisted-bgaware-r1",
"status": "completed_rejected",
"device": {
"requested": "cuda:0",
"observed": "NVIDIA GeForce RTX 4080 SUPER",
"torch": "2.11.0+cu128",
"ultralytics": "8.4.99"
},
"training": {
"epochs": 12,
"image_size": 640,
"batch_size": 8,
"workers": 0,
"seed": 20260809,
"base_model_sha256": "a9088b8491dfae36694b53e9e9406cb4e3511d334a5712fa34f75078a47759c1",
"candidate_best_sha256": "1337eb9fdd6bb73c525bd616e2ba961f20d585387db940576055afd38a71ca91",
"results_csv_sha256": "73bae1cc3e377fda8b1004a801c881f8313d6dffbbb5986555e2c5226212177d",
"args_yaml_sha256": "374613f927c57f9e9832cf7e0131c987dc978cbe1ea787a827030a8378385122"
},
"validation": {
"split": "val",
"image_count": 36,
"positive_image_count": 18,
"pure_background_image_count": 18,
"instance_count": 5686,
"baseline": {
"precision": 0.542,
"recall": 0.430,
"map50": 0.345,
"map50_95": 0.141,
"pure_background_detections_at_confidence_0_15": 0
},
"candidate_best": {
"precision": 0.530,
"recall": 0.435,
"map50": 0.337,
"map50_95": 0.135,
"pure_background_detections_at_confidence_0_15": 3
}
},
"decision": {
"promote": false,
"production_model_changed": false,
"reason": "The small recall gain does not compensate for lower precision and mAP plus a regression from zero to three detections on pure-background validation tiles.",
"active_model_sha256_after_decision": "a9088b8491dfae36694b53e9e9406cb4e3511d334a5712fa34f75078a47759c1"
},
"claim_boundary": "Experimental Kempen validation only. No protected test or challenge data was opened, no national accuracy claim is made, and formal human review remains required for any future promotion."
}