license: openrail++
language:
- en
base_model:
- facebook/detr-resnet-101
pipeline_tag: object-detection
tags:
- Baggage
Detects 3 following classes:
- backpack
- handbag
- suitcase
network resolution = 608 * 608
Loading weights from /BAG_DET_003.weights...
seen 64
Done! Loaded 176 layers from weights-file
calculation mAP (mean average precision)...
1204
detections_count = 7337, unique_truth_count = 2997
class_id = 0, name = backpack, ap = 75.79% (TP = 770, FP = 162)
class_id = 1, name = handbag, ap = 44.53% (TP = 439, FP = 227)
class_id = 2, name = suitcase, ap = 75.80% (TP = 503, FP = 108)
for conf_thresh = 0.25, precision = 0.78, recall = 0.57, F1-score = 0.66
for conf_thresh = 0.25, TP = 1712, FP = 497, FN = 1285, average IoU = 61.73 %
IoU threshold = 50 %, used Area-Under-Curve for each unique Recall
mean average precision (mAP@0.50) = 0.653740, or 65.37 %
Total Detection Time: 17.000000 Seconds