Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 1/3 2.56G 1.26 1.267 1.016 122 640: 100%|██████████| 533/533 [01:08<00:00, 7.75it/s]^ Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 267/267 [01:07<00:00, 3.93it/s] all 8519 114053 0.97 0.282 0.306 0.216 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 2/3 3.36G 1.001 0.7182 0.9132 154 640: 100%|██████████| 533/533 [00:59<00:00, 8.92it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 267/267 [01:07<00:00, 3.93it/s] all 8519 114053 0.969 0.288 0.31 0.225 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 3/3 3.37G 0.9513 0.6483 0.9023 127 640: 100%|██████████| 533/533 [00:59<00:00, 8.93it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 267/267 [01:21<00:00, 3.28it/s] all 8519 114053 0.973 0.294 0.323 0.233 3 epochs completed in 0.116 hours. Optimizer stripped from runs/detect/train3/weights/last.pt, 6.2MB Optimizer stripped from runs/detect/train3/weights/best.pt, 6.2MB Validating runs/detect/train3/weights/best.pt... Ultralytics YOLOv8.0.120 🚀 Python-3.9.7 torch-2.0.0+cu118 CUDA:0 (NVIDIA GeForce RTX 3090, 24265MiB) Model summary (fused): 168 layers, 3006428 parameters, 0 gradients Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 267/267 [01:19<00:00, 3.37it/s] all 8519 114053 0.973 0.294 0.323 0.233 frame 8519 36 1 0 0.000451 0.000198 body 8519 403 1 0 0.0344 0.0144 text 8519 113614 0.919 0.882 0.933 0.686 Speed: 0.1ms preprocess, 0.4ms inference, 0.0ms loss, 1.0ms postprocess per image