使⽤COCO数据集训练YOLOX

 

注意： 训练的时候，如果GPU不够，可以修改batchsize大小。 

(yolox) xuefei@f123:/mnt/d/BaiduNetdiskDownload/CV/YOLOX$ ls
LICENSE      README.md      assets  checkpoints  demo  exps        requirements.txt  setup.py  tools  yolox
MANIFEST.in  YOLOX_outputs  build   datasets     docs  hubconf.py  setup.cfg         tests     venv   yolox.egg-info

(yolox) xuefei@f123:/mnt/d/BaiduNetdiskDownload/CV/YOLOX$
(yolox) xuefei@f123:/mnt/d/BaiduNetdiskDownload/CV/YOLOX$ python -m yolox.tools.train -n yolox-s -d 1 -b 16 --fp16
2024-02-02 08:36:25 | INFO     | yolox.core.trainer:130 - args: Namespace(batch_size=16, cache=None, ckpt=None, devices=1, dist_backend='nccl', dist_url=None, exp_file=None, experiment_name='yolox_s', fp16=True, logger='tensorboard', machine_rank=0, name='yolox-s', num_machines=1, occupy=False, opts=[], resume=False, start_epoch=None)
2024-02-02 08:36:25 | INFO     | yolox.core.trainer:131 - exp value:
╒═══════════════════╤════════════════════════════╕
│ keys              │ values                     │
╞═══════════════════╪════════════════════════════╡
│ seed              │ None                       │
├───────────────────┼────────────────────────────┤
│ output_dir        │ './YOLOX_outputs'          │
├───────────────────┼────────────────────────────┤
│ print_interval    │ 10                         │
├───────────────────┼────────────────────────────┤
│ eval_interval     │ 10                         │
├───────────────────┼────────────────────────────┤
│ dataset           │ None                       │
├───────────────────┼────────────────────────────┤
│ num_classes       │ 80                         │
├───────────────────┼────────────────────────────┤
│ depth             │ 0.33                       │
├───────────────────┼────────────────────────────┤
│ width             │ 0.5                        │
├───────────────────┼────────────────────────────┤
│ act               │ 'silu'                     │
├───────────────────┼────────────────────────────┤
│ data_num_workers  │ 4                          │
├───────────────────┼────────────────────────────┤
│ input_size        │ (640, 640)                 │
├───────────────────┼────────────────────────────┤
│ multiscale_range  │ 5                          │
├───────────────────┼────────────────────────────┤
│ data_dir          │ None                       │
├───────────────────┼────────────────────────────┤
│ train_ann         │ 'instances_train2017.json' │
├───────────────────┼────────────────────────────┤
│ val_ann           │ 'instances_val2017.json'   │
├───────────────────┼────────────────────────────┤
│ test_ann          │ 'instances_test2017.json'  │
├───────────────────┼────────────────────────────┤
│ mosaic_prob       │ 1.0                        │
├───────────────────┼────────────────────────────┤
│ mixup_prob        │ 1.0                        │
├───────────────────┼────────────────────────────┤
│ hsv_prob          │ 1.0                        │
├───────────────────┼────────────────────────────┤
│ flip_prob         │ 0.5                        │
├───────────────────┼────────────────────────────┤
│ degrees           │ 10.0                       │
├───────────────────┼────────────────────────────┤
│ translate         │ 0.1                        │
├───────────────────┼────────────────────────────┤
│ mosaic_scale      │ (0.1, 2)                   │
├───────────────────┼────────────────────────────┤
│ enable_mixup      │ True                       │
├───────────────────┼────────────────────────────┤
│ mixup_scale       │ (0.5, 1.5)                 │
├───────────────────┼────────────────────────────┤
│ shear             │ 2.0                        │
├───────────────────┼────────────────────────────┤
│ warmup_epochs     │ 5                          │
├───────────────────┼────────────────────────────┤
│ max_epoch         │ 300                        │
├───────────────────┼────────────────────────────┤
│ warmup_lr         │ 0                          │
├───────────────────┼────────────────────────────┤
│ min_lr_ratio      │ 0.05                       │
├───────────────────┼────────────────────────────┤
│ basic_lr_per_img  │ 0.00015625                 │
├───────────────────┼────────────────────────────┤
│ scheduler         │ 'yoloxwarmcos'             │
├───────────────────┼────────────────────────────┤
│ no_aug_epochs     │ 15                         │
├───────────────────┼────────────────────────────┤
│ ema               │ True                       │
├───────────────────┼────────────────────────────┤
│ weight_decay      │ 0.0005                     │
├───────────────────┼────────────────────────────┤
│ momentum          │ 0.9                        │
├───────────────────┼────────────────────────────┤
│ save_history_ckpt │ True                       │
├───────────────────┼────────────────────────────┤
│ exp_name          │ 'yolox_s'                  │
├───────────────────┼────────────────────────────┤
│ test_size         │ (640, 640)                 │
├───────────────────┼────────────────────────────┤
│ test_conf         │ 0.01                       │
├───────────────────┼────────────────────────────┤
│ nmsthre           │ 0.65                       │
╘═══════════════════╧════════════════════════════╛
2024-02-02 08:36:25 | INFO     | yolox.core.trainer:137 - Model Summary: Params: 8.97M, Gflops: 26.93
2024-02-02 08:36:28 | INFO     | yolox.data.datasets.coco:63 - loading annotations into memory...
2024-02-02 08:36:38 | INFO     | yolox.data.datasets.coco:63 - Done (t=10.09s)
2024-02-02 08:36:38 | INFO     | pycocotools.coco:86 - creating index...
2024-02-02 08:36:39 | INFO     | pycocotools.coco:86 - index created!
2024-02-02 08:36:55 | INFO     | yolox.core.trainer:155 - init prefetcher, this might take one minute or less...
2024-02-02 08:36:58 | INFO     | yolox.data.datasets.coco:63 - loading annotations into memory...
2024-02-02 08:36:59 | INFO     | yolox.data.datasets.coco:63 - Done (t=0.58s)
2024-02-02 08:36:59 | INFO     | pycocotools.coco:86 - creating index...
2024-02-02 08:36:59 | INFO     | pycocotools.coco:86 - index created!
2024-02-02 08:36:59 | INFO     | yolox.core.trainer:191 - Training start...
2024-02-02 08:36:59 | INFO     | yolox.core.trainer:192 -
YOLOX(
  (backbone): YOLOPAFPN(
    (backbone): CSPDarknet(
      (stem): Focus(
        (conv): BaseConv(
          (conv): Conv2d(12, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(32, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (dark2): Sequential(
        (0): BaseConv(
          (conv): Conv2d(32, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (1): CSPLayer(
          (conv1): BaseConv(
            (conv): Conv2d(64, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(32, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (conv2): BaseConv(
            (conv): Conv2d(64, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(32, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (conv3): BaseConv(
            (conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (m): Sequential(
            (0): Bottleneck(
              (conv1): BaseConv(
                (conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(32, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
              (conv2): BaseConv(
                (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                (bn): BatchNorm2d(32, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
            )
          )
        )
      )
      (dark3): Sequential(
        (0): BaseConv(
          (conv): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (1): CSPLayer(
          (conv1): BaseConv(
            (conv): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (conv2): BaseConv(
            (conv): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (conv3): BaseConv(
            (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (m): Sequential(
            (0): Bottleneck(
              (conv1): BaseConv(
                (conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
              (conv2): BaseConv(
                (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
            )
            (1): Bottleneck(
              (conv1): BaseConv(
                (conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
              (conv2): BaseConv(
                (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
            )
            (2): Bottleneck(
              (conv1): BaseConv(
                (conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
              (conv2): BaseConv(
                (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
            )
          )
        )
      )
      (dark4): Sequential(
        (0): BaseConv(
          (conv): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (1): CSPLayer(
          (conv1): BaseConv(
            (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (conv2): BaseConv(
            (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (conv3): BaseConv(
            (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (m): Sequential(
            (0): Bottleneck(
              (conv1): BaseConv(
                (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
              (conv2): BaseConv(
                (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
            )
            (1): Bottleneck(
              (conv1): BaseConv(
                (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
              (conv2): BaseConv(
                (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
            )
            (2): Bottleneck(
              (conv1): BaseConv(
                (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
              (conv2): BaseConv(
                (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
            )
          )
        )
      )
      (dark5): Sequential(
        (0): BaseConv(
          (conv): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (1): SPPBottleneck(
          (conv1): BaseConv(
            (conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (m): ModuleList(
            (0): MaxPool2d(kernel_size=5, stride=1, padding=2, dilation=1, ceil_mode=False)
            (1): MaxPool2d(kernel_size=9, stride=1, padding=4, dilation=1, ceil_mode=False)
            (2): MaxPool2d(kernel_size=13, stride=1, padding=6, dilation=1, ceil_mode=False)
          )
          (conv2): BaseConv(
            (conv): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
        (2): CSPLayer(
          (conv1): BaseConv(
            (conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (conv2): BaseConv(
            (conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (conv3): BaseConv(
            (conv): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (m): Sequential(
            (0): Bottleneck(
              (conv1): BaseConv(
                (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
              (conv2): BaseConv(
                (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
            )
          )
        )
      )
    )
    (upsample): Upsample(scale_factor=2.0, mode=nearest)
    (lateral_conv0): BaseConv(
      (conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (C3_p4): CSPLayer(
      (conv1): BaseConv(
        (conv): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (conv2): BaseConv(
        (conv): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (conv3): BaseConv(
        (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (conv1): BaseConv(
            (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (conv2): BaseConv(
            (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
      )
    )
    (reduce_conv1): BaseConv(
      (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (C3_p3): CSPLayer(
      (conv1): BaseConv(
        (conv): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (conv2): BaseConv(
        (conv): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (conv3): BaseConv(
        (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (conv1): BaseConv(
            (conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (conv2): BaseConv(
            (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
      )
    )
    (bu_conv2): BaseConv(
      (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
      (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (C3_n3): CSPLayer(
      (conv1): BaseConv(
        (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (conv2): BaseConv(
        (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (conv3): BaseConv(
        (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (conv1): BaseConv(
            (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (conv2): BaseConv(
            (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
      )
    )
    (bu_conv1): BaseConv(
      (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
      (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (C3_n4): CSPLayer(
      (conv1): BaseConv(
        (conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (conv2): BaseConv(
        (conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (conv3): BaseConv(
        (conv): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (conv1): BaseConv(
            (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (conv2): BaseConv(
            (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
      )
    )
  )
  (head): YOLOXHead(
    (cls_convs): ModuleList(
      (0): Sequential(
        (0): BaseConv(
          (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (1): BaseConv(
          (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (1): Sequential(
        (0): BaseConv(
          (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (1): BaseConv(
          (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (2): Sequential(
        (0): BaseConv(
          (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (1): BaseConv(
          (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
    )
    (reg_convs): ModuleList(
      (0): Sequential(
        (0): BaseConv(
          (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (1): BaseConv(
          (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (1): Sequential(
        (0): BaseConv(
          (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (1): BaseConv(
          (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (2): Sequential(
        (0): BaseConv(
          (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (1): BaseConv(
          (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
    )
    (cls_preds): ModuleList(
      (0): Conv2d(128, 80, kernel_size=(1, 1), stride=(1, 1))
      (1): Conv2d(128, 80, kernel_size=(1, 1), stride=(1, 1))
      (2): Conv2d(128, 80, kernel_size=(1, 1), stride=(1, 1))
    )
    (reg_preds): ModuleList(
      (0): Conv2d(128, 4, kernel_size=(1, 1), stride=(1, 1))
      (1): Conv2d(128, 4, kernel_size=(1, 1), stride=(1, 1))
      (2): Conv2d(128, 4, kernel_size=(1, 1), stride=(1, 1))
    )
    (obj_preds): ModuleList(
      (0): Conv2d(128, 1, kernel_size=(1, 1), stride=(1, 1))
      (1): Conv2d(128, 1, kernel_size=(1, 1), stride=(1, 1))
      (2): Conv2d(128, 1, kernel_size=(1, 1), stride=(1, 1))
    )
    (stems): ModuleList(
      (0): BaseConv(
        (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (1): BaseConv(
        (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (2): BaseConv(
        (conv): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
    )
    (l1_loss): L1Loss()
    (bcewithlog_loss): BCEWithLogitsLoss()
    (iou_loss): IOUloss()
  )
)
2024-02-02 08:36:59 | INFO     | yolox.core.trainer:203 - ---> start train epoch1
2024-02-02 08:37:07 | INFO     | yolox.core.trainer:263 - epoch: 1/300, iter: 10/7393, gpu mem: 3713Mb, mem: 6.5Gb, iter_time: 0.751s, data_time: 0.008s, total_loss: 20.3, iou_loss: 4.8, l1_loss: 0.0, conf_loss: 13.7, cls_loss: 1.9, lr: 1.830e-10, size: 640, ETA: 19 days, 6:56:56
2024-02-02 08:37:12 | INFO     | yolox.core.trainer:263 - epoch: 1/300, iter: 20/7393, gpu mem: 3713Mb, mem: 6.5Gb, iter_time: 0.467s, data_time: 0.001s, total_loss: 15.7, iou_loss: 4.6, l1_loss: 0.0, conf_loss: 9.0, cls_loss: 2.1, lr: 7.318e-10, size: 640, ETA: 15 days, 15:17:49
2024-02-02 08:37:18 | INFO     | yolox.core.trainer:263 - epoch: 1/300, iter: 30/7393, gpu mem: 3713Mb, mem: 6.5Gb, iter_time: 0.616s, data_time: 0.002s, total_loss: 16.7, iou_loss: 4.6, l1_loss: 0.0, conf_loss: 10.0, cls_loss: 2.1, lr: 1.647e-09, size: 576, ETA: 15 days, 16:38:41
2024-02-02 08:37:30 | INFO     | yolox.core.trainer:263 - epoch: 1/300, iter: 40/7393, gpu mem: 4978Mb, mem: 6.5Gb, iter_time: 1.207s, data_time: 0.002s, total_loss: 17.8, iou_loss: 4.7, l1_loss: 0.0, conf_loss: 11.1, cls_loss: 2.0, lr: 2.927e-09, size: 800, ETA: 19 days, 12:21:38
2024-02-02 08:37:36 | INFO     | yolox.core.trainer:263 - epoch: 1/300, iter: 50/7393, gpu mem: 4978Mb, mem: 6.5Gb, iter_time: 0.630s, data_time: 0.002s, total_loss: 15.8, iou_loss: 4.7, l1_loss: 0.0, conf_loss: 8.9, cls_loss: 2.2, lr: 4.574e-09, size: 544, ETA: 18 days, 20:17:13
2024-02-02 08:37:45 | INFO     | yolox.core.trainer:263 - epoch: 1/300, iter: 60/7393, gpu mem: 4978Mb, mem: 6.5Gb, iter_time: 0.916s, data_time: 0.002s, total_loss: 17.5, iou_loss: 4.7, l1_loss: 0.0, conf_loss: 10.9, cls_loss: 1.9, lr: 6.587e-09, size: 736, ETA: 19 days, 14:59:49
2024-02-02 08:37:55 | INFO     | yolox.core.trainer:263 - epoch: 1/300, iter: 70/7393, gpu mem: 5059Mb, mem: 6.5Gb, iter_time: 0.994s, data_time: 0.002s, total_loss: 18.5, iou_loss: 4.6, l1_loss: 0.0, conf_loss: 11.8, cls_loss: 2.1, lr: 8.965e-09, size: 800, ETA: 20 days, 11:11:27
2024-02-02 08:38:03 | INFO     | yolox.core.trainer:263 - epoch: 1/300, iter: 80/7393, gpu mem: 5059Mb, mem: 6.5Gb, iter_time: 0.816s, data_time: 0.003s, total_loss: 20.7, iou_loss: 4.7, l1_loss: 0.0, conf_loss: 13.8, cls_loss: 2.2, lr: 1.171e-08, size: 800, ETA: 20 days, 12:36:00
2024-02-02 08:38:10 | INFO     | yolox.core.trainer:263 - epoch: 1/300, iter: 90/7393, gpu mem: 5059Mb, mem: 6.5Gb, iter_time: 0.631s, data_time: 0.002s, total_loss: 18.8, iou_loss: 4.6, l1_loss: 0.0, conf_loss: 12.3, cls_loss: 1.9, lr: 1.482e-08, size: 640, ETA: 20 days, 1:04:39
2024-02-02 08:38:15 | INFO     | yolox.core.trainer:263 - epoch: 1/300, iter: 100/7393, gpu mem: 5059Mb, mem: 6.5Gb, iter_time: 0.504s, data_time: 0.002s, total_loss: 15.7, iou_loss: 4.6, l1_loss: 0.0, conf_loss: 9.1, cls_loss: 2.0, lr: 1.830e-08, size: 480, ETA: 19 days, 8:00:53
2024-02-02 08:38:22 | INFO     | yolox.core.trainer:263 - epoch: 1/300, iter: 110/7393, gpu mem: 5059Mb, mem: 6.5Gb, iter_time: 0.746s, data_time: 0.002s, total_loss: 18.6, iou_loss: 4.7, l1_loss: 0.0, conf_loss: 11.8, cls_loss: 2.1, lr: 2.214e-08, size: 672, ETA: 19 days, 7:36:25
2024-02-02 08:38:27 | INFO     | yolox.core.trainer:263 - epoch: 1/300, iter: 120/7393, gpu mem: 5059Mb, mem: 6.5Gb, iter_time: 0.519s, data_time: 0.002s, total_loss: 15.7, iou_loss: 4.6, l1_loss: 0.0, conf_loss: 9.0, cls_loss: 2.0, lr: 2.635e-08, size: 512, ETA: 18 days, 19:38:05
2024-02-02 08:38:32 | INFO     | yolox.core.trainer:263 - epoch: 1/300, iter: 130/7393, gpu mem: 5059Mb, mem: 6.5Gb, iter_time: 0.463s, data_time: 0.001s, total_loss: 17.6, iou_loss: 4.7, l1_loss: 0.0, conf_loss: 11.1, cls_loss: 1.9, lr: 3.092e-08, size: 640, ETA: 18 days, 6:51:07

^C2024-02-02 08:38:32 | INFO     | yolox.core.trainer:196 - Training of experiment is done and the best AP is 0.00