epoch 100

batch 2

optimizer: 'optimizer=auto' found, ignoring 'lr0=0.01' and 'momentum=0.937' and determining best 'optimizer', 'lr0' and 'momentum' automatically...

optimizer: AdamW(lr=0.00125, momentum=0.9) with parameter groups 57 weight(decay=0.0), 64 weight(decay=0.0005), 63 bias(decay=0.0)

Image sizes 640 train, 640 val

Using 8 dataloader workers

Logging results to runs/detect/train5

Starting training for 100 epochs...

Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size

1/100     0.696G      1.638      2.754      1.616          2        640: 100%|██████████| 1666/1666 [04:07<00:00,  6.73it/s]

Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 261/261 [01:01<00:00,  4.22it/s]

all       1042       1046      0.464       0.46       0.41      0.209

Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size

2/100     0.721G      1.542      2.033      1.555          1        640: 100%|██████████| 1666/1666 [03:45<00:00,  7.38it/s]

Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 261/261 [01:13<00:00,  3.54it/s]

all       1042       1046      0.488      0.517      0.462      0.209