[2026-10-14 15:07:47] [WARNING] rf-detr - Using a different number of positional encodings than DINOv2, which means we're not loading DINOv2 backbone weights. This is not a problem if finetuning a pretrained RF-DETR model.
[2026-10-14 15:07:47] [WARNING] rf-detr - Using patch size 12 instead of 14, which means we're not loading DINOv2 backbone weights. This is not a problem if finetuning a pretrained RF-DETR model.
[2026-10-14 15:07:48] [WARNING] rf-detr - Model is not optimized for inference. Latency may be higher than expected. For full GPU throughput (e.g. ~8x on T4 via FP16 Tensor Cores), call model.inference(dtype=torch.float16).
loading annotations into memory...
Done (t=0.00s)
creating index...
index created!
Loading and preparing results...
DONE (t=0.01s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *segm*
DONE (t=0.05s).
Accumulating evaluation results...
DONE (t=0.01s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.427
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.658
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.515
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.419
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.446
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.420
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.465
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.485
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.458
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.525
{"stage": "select", "model": "medium", "threshold": 0.7, "metrics": [{"calibration": [{"f1_at_iou_50": 0.26666666666666666, "failed_gt_instances": 8, "false_negatives": 8, "false_positives": 58, "hole_background_iou": 0.10690143190143189, "matched_mask_iou": 0.6107738641287257, "threshold": 0.05, "true_positives": 12}, {"f1_at_iou_50": 0.42857142857142855, "failed_gt_instances": 8, "false_negatives": 8, "false_positives": 24, "hole_background_iou": 0.0, "matched_mask_iou": 0.5352881176835468, "threshold": 0.1, "true_positives": 12}, {"f1_at_iou_50": 0.4897959183673469, "failed_gt_instances": 8, "false_negatives": 8, "false_positives": 17, "hole_background_iou": 0.0, "matched_mask_iou": 0.5352881176835468, "threshold": 0.15, "true_positives": 12}, {"f1_at_iou_50": 0.5454545454545454, "failed_gt_instances": 8, "false_negatives": 8, "false_positives": 12, "hole_background_iou": 0.0, "matched_mask_iou": 0.5352881176835468, "threshold": 0.2, "true_positives": 12}, {"f1_at_iou_50": 0.631578947368421, "failed_gt_instances": 8, "false_negatives": 8, "false_positives": 6, "hole_background_iou": 0.0, "matched_mask_iou": 0.5250454442119972, "threshold": 0.3, "true_positives": 12}, {"f1_at_iou_50": 0.6857142857142857, "failed_gt_instances": 8, "false_negatives": 8, "false_positives": 3, "hole_background_iou": 0.0, "matched_mask_iou": 0.5152080867337945, "threshold": 0.4, "true_positives": 12}, {"f1_at_iou_50": 0.6857142857142857, "failed_gt_instances": 8, "false_negatives": 8, "false_positives": 3, "hole_background_iou": 0.0, "matched_mask_iou": 0.5152080867337945, "threshold": 0.5, "true_positives": 12}, {"f1_at_iou_50": 0.6857142857142857, "failed_gt_instances": 8, "false_negatives": 8, "false_positives": 3, "hole_background_iou": 0.0, "matched_mask_iou": 0.5152080867337945, "threshold": 0.6, "true_positives": 12}, {"f1_at_iou_50": 0.7058823529411765, "failed_gt_instances": 8, "false_negatives": 8, "false_positives": 2, "hole_background_iou": 0.0, "matched_mask_iou": 0.5152080867337945, "threshold": 0.7, "true_positives": 12}, {"f1_at_iou_50": 0.7272727272727273, "failed_gt_instances": 8, "false_negatives": 8, "false_positives": 1, "hole_background_iou": 0.0, "matched_mask_iou": 0.5131886132393841, "threshold": 0.8, "true_positives": 12}], "checkpoint_sha256": "40a603240dfd67390ae193588819e47a4860339b2642ffe8e631ffe3c876e98e", "failed_gt_instances": 8, "hole_background_iou": 0.0, "mask_ap_50": 0.626905337993088, "mask_ap_50_95": 0.4109541101569446, "matched_mask_iou": 0.5131886132393841, "model": "small", "peak_cuda_memory_bytes": 3447890944, "scope": "internal_group_validation_used_for_selection", "selected_threshold": 0.8, "training_elapsed_seconds": 1366.32999259606, "validation_frames": 14, "validation_inference_seconds": 10.547415417036973, "validation_instances": 20}, {"model": "medium", "mask_ap_50_95": 0.4266613337157892, "mask_ap_50": 0.6576611821186203, "calibration": [{"threshold": 0.05, "true_positives": 15, "false_positives": 69, "false_negatives": 5, "f1_at_iou_50": 0.28846153846153844, "matched_mask_iou": 0.6537406989773688, "hole_background_iou": 0.0017123287671232876, "failed_gt_instances": 5}, {"threshold": 0.1, "true_positives": 13, "false_positives": 27, "false_negatives": 7, "f1_at_iou_50": 0.43333333333333335, "matched_mask_iou": 0.5460991944738696, "hole_background_iou": 0.0, "failed_gt_instances": 7}, {"threshold": 0.15, "true_positives": 13, "false_positives": 18, "false_negatives": 7, "f1_at_iou_50": 0.5098039215686274, "matched_mask_iou": 0.5460991944738696, "hole_background_iou": 0.0, "failed_gt_instances": 7}, {"threshold": 0.2, "true_positives": 12, "false_positives": 9, "false_negatives": 8, "f1_at_iou_50": 0.5853658536585366, "matched_mask_iou": 0.5154361980961559, "hole_background_iou": 0.0, "failed_gt_instances": 8}, {"threshold": 0.3, "true_positives": 12, "false_positives": 6, "false_negatives": 8, "f1_at_iou_50": 0.631578947368421, "matched_mask_iou": 0.5154361980961559, "hole_background_iou": 0.0, "failed_gt_instances": 8}, {"threshold": 0.4, "true_positives": 12, "false_positives": 5, "false_negatives": 8, "f1_at_iou_50": 0.6486486486486487, "matched_mask_iou": 0.5154361980961559, "hole_background_iou": 0.0, "failed_gt_instances": 8}, {"threshold": 0.5, "true_positives": 12, "false_positives": 4, "false_negatives": 8, "f1_at_iou_50": 0.6666666666666666, "matched_mask_iou": 0.5154361980961559, "hole_background_iou": 0.0, "failed_gt_instances": 8}, {"threshold": 0.6, "true_positives": 12, "false_positives": 2, "false_negatives": 8, "f1_at_iou_50": 0.7058823529411765, "matched_mask_iou": 0.5111945528519399, "hole_background_iou": 0.0, "failed_gt_instances": 8}, {"threshold": 0.7, "true_positives": 12, "false_positives": 2, "false_negatives": 8, "f1_at_iou_50": 0.7058823529411765, "matched_mask_iou": 0.5111945528519399, "hole_background_iou": 0.0, "failed_gt_instances": 8}, {"threshold": 0.8, "true_positives": 11, "false_positives": 1, "false_negatives": 9, "f1_at_iou_50": 0.6875, "matched_mask_iou": 0.47024888320482566, "hole_background_iou": 0.0, "failed_gt_instances": 9}], "selected_threshold": 0.7, "matched_mask_iou": 0.5111945528519399, "hole_background_iou": 0.0, "failed_gt_instances": 8, "validation_frames": 14, "validation_instances": 20, "validation_inference_seconds": 26.968713652109727, "training_elapsed_seconds": 1513.1105900140246, "peak_cuda_memory_bytes": 4490103808, "checkpoint_sha256": "2643da292f03712808232ae474d4b7300e7d26e0bc6a57db5227d8d023b3b678", "scope": "internal_group_validation_used_for_selection"}]}
