devbox
从前慢现在也慢
这个屌丝很懒，什么也没留下！
关注作者
热门标签
热门文章
当前位置:   article > 正文

使用RegNet替换YOLOX中原始的Backbone

作者：从前慢现在也慢 | 2024-02-22 10:49:23

赞

踩

使用RegNet替换YOLOX中原始的Backbone

使用mmdetection 中的RegNet bcakbones替换YOLOX中原始的Backbone

将mmdet/models/backbones/regnet.py中相关的代码复制到YOLOX中，并进行适配

注意通道数要适配

in_channels = [64, 160, 384]

，可以通过调试后，先运行到后后端输出结果出，打印出通道数，得到通道后，在写到这个地方。

 

  1. (yolox) xuefei@f123:/mnt/d/work/study/detect/8$ python -m yolox.tools.train  -f exps/kitti_car_detection/yolox_regnet.py        -d 0 -b 16 --fp16
  2. 2024-02-18 22:17:51 | INFO     | yolox.core.trainer:126 - args: Namespace(batch_size=16, cache=False, ckpt=None, devices=0, dist_backend='nccl', dist_url=None, exp_file='exps/kitti_car_detection/yolox_regnet.py', experiment_name='yolox_regnet', fp16=True, logger='tensorboard', machine_rank=0, name=None, num_machines=1, occupy=False, opts=[], resume=False, start_epoch=None)
  3. 2024-02-18 22:17:51 | INFO     | yolox.core.trainer:127 - exp value:
  4. ╒═══════════════════╤═══════════════════════════════════════════════════════════════╕
  5. │ keys              │ values                                                        │
  6. ╞═══════════════════╪═══════════════════════════════════════════════════════════════╡
  7. │ seed              │ None                                                          │
  8. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  9. │ output_dir        │ './YOLOX_outputs'                                             │
  10. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  11. │ print_interval    │ 10                                                            │
  12. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  13. │ eval_interval     │ 10                                                            │
  14. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  15. │ num_classes       │ 7                                                             │
  16. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  17. │ depth             │ 1.0                                                           │
  18. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  19. │ width             │ 0.5                                                           │
  20. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  21. │ act               │ 'silu'                                                        │
  22. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  23. │ data_num_workers  │ 16                                                            │
  24. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  25. │ input_size        │ (256, 832)                                                    │
  26. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  27. │ multiscale_range  │ 5                                                             │
  28. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  29. │ data_dir          │ '/mnt/d/BaiduNetdiskDownload/CV/KITTI/KITTI_YOLOX/img/'       │
  30. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  31. │ train_ann         │ '/mnt/d/BaiduNetdiskDownload/CV/KITTI/KITTI_YOLOX/train.json' │
  32. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  33. │ val_ann           │ '/mnt/d/BaiduNetdiskDownload/CV/KITTI/KITTI_YOLOX/val.json'   │
  34. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  35. │ test_ann          │ '/mnt/d/BaiduNetdiskDownload/CV/KITTI/KITTI_YOLOX/test.json'  │
  36. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  37. │ mosaic_prob       │ 1.0                                                           │
  38. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  39. │ mixup_prob        │ 1.0                                                           │
  40. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  41. │ hsv_prob          │ 1.0                                                           │
  42. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  43. │ flip_prob         │ 0.5                                                           │
  44. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  45. │ degrees           │ 10.0                                                          │
  46. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  47. │ translate         │ 0.1                                                           │
  48. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  49. │ mosaic_scale      │ (0.1, 2)                                                      │
  50. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  51. │ enable_mixup      │ True                                                          │
  52. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  53. │ mixup_scale       │ (0.5, 1.5)                                                    │
  54. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  55. │ shear             │ 2.0                                                           │
  56. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  57. │ warmup_epochs     │ 5                                                             │
  58. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  59. │ max_epoch         │ 300                                                           │
  60. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  61. │ warmup_lr         │ 0                                                             │
  62. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  63. │ min_lr_ratio      │ 0.05                                                          │
  64. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  65. │ basic_lr_per_img  │ 0.00015625                                                    │
  66. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  67. │ scheduler         │ 'yoloxwarmcos'                                                │
  68. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  69. │ no_aug_epochs     │ 80                                                            │
  70. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  71. │ ema               │ True                                                          │
  72. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  73. │ weight_decay      │ 0.0005                                                        │
  74. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  75. │ momentum          │ 0.9                                                           │
  76. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  77. │ save_history_ckpt │ True                                                          │
  78. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  79. │ exp_name          │ 'yolox_regnet'                                                │
  80. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  81. │ test_size         │ (256, 832)                                                    │
  82. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  83. │ test_conf         │ 0.01                                                          │
  84. ├───────────────────┼───────────────────────────────────────────────────────────────┤
  85. │ nmsthre           │ 0.65                                                          │
  86. ╘═══════════════════╧═══════════════════════════════════════════════════════════════╛
  87. 2024-02-18 22:17:52 | INFO     | yolox.core.trainer:133 - Model Summary: Params: 8.90M, Gflops: 10.70
  88. 2024-02-18 22:17:54 | INFO     | yolox.data.datasets.kitti:64 - loading annotations into memory...
  89. 2024-02-18 22:17:55 | INFO     | yolox.data.datasets.kitti:64 - Done (t=0.08s)
  90. 2024-02-18 22:17:55 | INFO     | pycocotools.coco:86 - creating index...
  91. 2024-02-18 22:17:55 | INFO     | pycocotools.coco:86 - index created!
  92. 2024-02-18 22:17:55 | INFO     | yolox.core.trainer:151 - init prefetcher, this might take one minute or less...
  93. 2024-02-18 22:18:07 | INFO     | yolox.data.datasets.kitti:64 - loading annotations into memory...
  94. 2024-02-18 22:18:08 | INFO     | yolox.data.datasets.kitti:64 - Done (t=0.11s)
  95. 2024-02-18 22:18:08 | INFO     | pycocotools.coco:86 - creating index...
  96. 2024-02-18 22:18:08 | INFO     | pycocotools.coco:86 - index created!
  97. 2024-02-18 22:18:08 | INFO     | yolox.core.trainer:187 - Training start...
  98. 2024-02-18 22:18:08 | INFO     | yolox.core.trainer:188 -
  99. YOLOX(
  100.   (backbone): YOLOPAFPNRegNet(
  101.     (backbone): RegNet(
  102.       (conv1): Conv2d(3, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
  103.       (bn1): BatchNorm2d(32, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  104.       (relu): ReLU(inplace=True)
  105.       (layer1): ResLayer(
  106.         (0): Bottleneck(
  107.           (conv1): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
  108.           (bn1): BatchNorm2d(32, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  109.           (conv2): Conv2d(32, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=2, bias=False)
  110.           (bn2): BatchNorm2d(32, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  111.           (conv3): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
  112.           (bn3): BatchNorm2d(32, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  113.           (relu): ReLU(inplace=True)
  114.           (downsample): Sequential(
  115.             (0): Conv2d(32, 32, kernel_size=(1, 1), stride=(2, 2), bias=False)
  116.             (1): BatchNorm2d(32, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  117.           )
  118.         )
  119.         init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}}
  120.       )
  121.       (layer2): ResLayer(
  122.         (0): Bottleneck(
  123.           (conv1): Conv2d(32, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
  124.           (bn1): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  125.           (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=4, bias=False)
  126.           (bn2): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  127.           (conv3): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
  128.           (bn3): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  129.           (relu): ReLU(inplace=True)
  130.           (downsample): Sequential(
  131.             (0): Conv2d(32, 64, kernel_size=(1, 1), stride=(2, 2), bias=False)
  132.             (1): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  133.           )
  134.         )
  135.         init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}}
  136.         (1): Bottleneck(
  137.           (conv1): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
  138.           (bn1): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  139.           (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=4, bias=False)
  140.           (bn2): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  141.           (conv3): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
  142.           (bn3): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  143.           (relu): ReLU(inplace=True)
  144.         )
  145.         init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}}
  146.       )
  147.       (layer3): ResLayer(
  148.         (0): Bottleneck(
  149.           (conv1): Conv2d(64, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
  150.           (bn1): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  151.           (conv2): Conv2d(160, 160, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=10, bias=False)
  152.           (bn2): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  153.           (conv3): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
  154.           (bn3): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  155.           (relu): ReLU(inplace=True)
  156.           (downsample): Sequential(
  157.             (0): Conv2d(64, 160, kernel_size=(1, 1), stride=(2, 2), bias=False)
  158.             (1): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  159.           )
  160.         )
  161.         init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}}
  162.         (1): Bottleneck(
  163.           (conv1): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
  164.           (bn1): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  165.           (conv2): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=10, bias=False)
  166.           (bn2): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  167.           (conv3): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
  168.           (bn3): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  169.           (relu): ReLU(inplace=True)
  170.         )
  171.         init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}}
  172.         (2): Bottleneck(
  173.           (conv1): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
  174.           (bn1): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  175.           (conv2): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=10, bias=False)
  176.           (bn2): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  177.           (conv3): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
  178.           (bn3): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  179.           (relu): ReLU(inplace=True)
  180.         )
  181.         init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}}
  182.         (3): Bottleneck(
  183.           (conv1): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
  184.           (bn1): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  185.           (conv2): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=10, bias=False)
  186.           (bn2): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  187.           (conv3): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
  188.           (bn3): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  189.           (relu): ReLU(inplace=True)
  190.         )
  191.         init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}}
  192.         (4): Bottleneck(
  193.           (conv1): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
  194.           (bn1): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  195.           (conv2): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=10, bias=False)
  196.           (bn2): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  197.           (conv3): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
  198.           (bn3): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  199.           (relu): ReLU(inplace=True)
  200.         )
  201.         init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}}
  202.         (5): Bottleneck(
  203.           (conv1): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
  204.           (bn1): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  205.           (conv2): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=10, bias=False)
  206.           (bn2): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  207.           (conv3): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
  208.           (bn3): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  209.           (relu): ReLU(inplace=True)
  210.         )
  211.         init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}}
  212.         (6): Bottleneck(
  213.           (conv1): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
  214.           (bn1): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  215.           (conv2): Conv2d(160, 160, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=10, bias=False)
  216.           (bn2): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  217.           (conv3): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
  218.           (bn3): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  219.           (relu): ReLU(inplace=True)
  220.         )
  221.         init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}}
  222.       )
  223.       (layer4): ResLayer(
  224.         (0): Bottleneck(
  225.           (conv1): Conv2d(160, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
  226.           (bn1): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  227.           (conv2): Conv2d(384, 384, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=24, bias=False)
  228.           (bn2): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  229.           (conv3): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
  230.           (bn3): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  231.           (relu): ReLU(inplace=True)
  232.           (downsample): Sequential(
  233.             (0): Conv2d(160, 384, kernel_size=(1, 1), stride=(2, 2), bias=False)
  234.             (1): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  235.           )
  236.         )
  237.         init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}}
  238.         (1): Bottleneck(
  239.           (conv1): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
  240.           (bn1): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  241.           (conv2): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=24, bias=False)
  242.           (bn2): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  243.           (conv3): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
  244.           (bn3): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  245.           (relu): ReLU(inplace=True)
  246.         )
  247.         init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}}
  248.         (2): Bottleneck(
  249.           (conv1): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
  250.           (bn1): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  251.           (conv2): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=24, bias=False)
  252.           (bn2): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  253.           (conv3): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
  254.           (bn3): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  255.           (relu): ReLU(inplace=True)
  256.         )
  257.         init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}}
  258.         (3): Bottleneck(
  259.           (conv1): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
  260.           (bn1): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  261.           (conv2): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=24, bias=False)
  262.           (bn2): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  263.           (conv3): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
  264.           (bn3): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  265.           (relu): ReLU(inplace=True)
  266.         )
  267.         init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}}
  268.         (4): Bottleneck(
  269.           (conv1): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
  270.           (bn1): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  271.           (conv2): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=24, bias=False)
  272.           (bn2): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  273.           (conv3): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
  274.           (bn3): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  275.           (relu): ReLU(inplace=True)
  276.         )
  277.         init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}}
  278.         (5): Bottleneck(
  279.           (conv1): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
  280.           (bn1): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  281.           (conv2): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=24, bias=False)
  282.           (bn2): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  283.           (conv3): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
  284.           (bn3): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  285.           (relu): ReLU(inplace=True)
  286.         )
  287.         init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}}
  288.         (6): Bottleneck(
  289.           (conv1): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
  290.           (bn1): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  291.           (conv2): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=24, bias=False)
  292.           (bn2): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  293.           (conv3): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
  294.           (bn3): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  295.           (relu): ReLU(inplace=True)
  296.         )
  297.         init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}}
  298.         (7): Bottleneck(
  299.           (conv1): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
  300.           (bn1): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  301.           (conv2): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=24, bias=False)
  302.           (bn2): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  303.           (conv3): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
  304.           (bn3): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  305.           (relu): ReLU(inplace=True)
  306.         )
  307.         init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}}
  308.         (8): Bottleneck(
  309.           (conv1): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
  310.           (bn1): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  311.           (conv2): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=24, bias=False)
  312.           (bn2): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  313.           (conv3): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
  314.           (bn3): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  315.           (relu): ReLU(inplace=True)
  316.         )
  317.         init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}}
  318.         (9): Bottleneck(
  319.           (conv1): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
  320.           (bn1): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  321.           (conv2): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=24, bias=False)
  322.           (bn2): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  323.           (conv3): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
  324.           (bn3): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  325.           (relu): ReLU(inplace=True)
  326.         )
  327.         init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}}
  328.         (10): Bottleneck(
  329.           (conv1): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
  330.           (bn1): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  331.           (conv2): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=24, bias=False)
  332.           (bn2): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  333.           (conv3): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
  334.           (bn3): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  335.           (relu): ReLU(inplace=True)
  336.         )
  337.         init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}}
  338.         (11): Bottleneck(
  339.           (conv1): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
  340.           (bn1): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  341.           (conv2): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=24, bias=False)
  342.           (bn2): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  343.           (conv3): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
  344.           (bn3): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  345.           (relu): ReLU(inplace=True)
  346.         )
  347.         init_cfg={'type': 'Constant', 'val': 0, 'override': {'name': 'norm3'}}
  348.       )
  349.     )
  350.     init_cfg=[{'type': 'Kaiming', 'layer': 'Conv2d'}, {'type': 'Constant', 'val': 1, 'layer': ['_BatchNorm', 'GroupNorm']}]
  351.     (upsample): Upsample(scale_factor=2.0, mode=nearest)
  352.     (lateral_conv0): BaseConv(
  353.       (conv): Conv2d(384, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
  354.       (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  355.       (act): SiLU(inplace=True)
  356.     )
  357.     (C3_p4): CSPLayer(
  358.       (conv1): BaseConv(
  359.         (conv): Conv2d(320, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)
  360.         (bn): BatchNorm2d(80, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  361.         (act): SiLU(inplace=True)
  362.       )
  363.       (conv2): BaseConv(
  364.         (conv): Conv2d(320, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)
  365.         (bn): BatchNorm2d(80, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  366.         (act): SiLU(inplace=True)
  367.       )
  368.       (conv3): BaseConv(
  369.         (conv): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
  370.         (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  371.         (act): SiLU(inplace=True)
  372.       )
  373.       (m): Sequential(
  374.         (0): Bottleneck(
  375.           (conv1): BaseConv(
  376.             (conv): Conv2d(80, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)
  377.             (bn): BatchNorm2d(80, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  378.             (act): SiLU(inplace=True)
  379.           )
  380.           (conv2): BaseConv(
  381.             (conv): Conv2d(80, 80, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  382.             (bn): BatchNorm2d(80, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  383.             (act): SiLU(inplace=True)
  384.           )
  385.         )
  386.         (1): Bottleneck(
  387.           (conv1): BaseConv(
  388.             (conv): Conv2d(80, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)
  389.             (bn): BatchNorm2d(80, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  390.             (act): SiLU(inplace=True)
  391.           )
  392.           (conv2): BaseConv(
  393.             (conv): Conv2d(80, 80, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  394.             (bn): BatchNorm2d(80, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  395.             (act): SiLU(inplace=True)
  396.           )
  397.         )
  398.         (2): Bottleneck(
  399.           (conv1): BaseConv(
  400.             (conv): Conv2d(80, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)
  401.             (bn): BatchNorm2d(80, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  402.             (act): SiLU(inplace=True)
  403.           )
  404.           (conv2): BaseConv(
  405.             (conv): Conv2d(80, 80, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  406.             (bn): BatchNorm2d(80, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  407.             (act): SiLU(inplace=True)
  408.           )
  409.         )
  410.       )
  411.     )
  412.     (reduce_conv1): BaseConv(
  413.       (conv): Conv2d(160, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
  414.       (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  415.       (act): SiLU(inplace=True)
  416.     )
  417.     (C3_p3): CSPLayer(
  418.       (conv1): BaseConv(
  419.         (conv): Conv2d(128, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
  420.         (bn): BatchNorm2d(32, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  421.         (act): SiLU(inplace=True)
  422.       )
  423.       (conv2): BaseConv(
  424.         (conv): Conv2d(128, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
  425.         (bn): BatchNorm2d(32, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  426.         (act): SiLU(inplace=True)
  427.       )
  428.       (conv3): BaseConv(
  429.         (conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
  430.         (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  431.         (act): SiLU(inplace=True)
  432.       )
  433.       (m): Sequential(
  434.         (0): Bottleneck(
  435.           (conv1): BaseConv(
  436.             (conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
  437.             (bn): BatchNorm2d(32, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  438.             (act): SiLU(inplace=True)
  439.           )
  440.           (conv2): BaseConv(
  441.             (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  442.             (bn): BatchNorm2d(32, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  443.             (act): SiLU(inplace=True)
  444.           )
  445.         )
  446.         (1): Bottleneck(
  447.           (conv1): BaseConv(
  448.             (conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
  449.             (bn): BatchNorm2d(32, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  450.             (act): SiLU(inplace=True)
  451.           )
  452.           (conv2): BaseConv(
  453.             (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  454.             (bn): BatchNorm2d(32, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  455.             (act): SiLU(inplace=True)
  456.           )
  457.         )
  458.         (2): Bottleneck(
  459.           (conv1): BaseConv(
  460.             (conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
  461.             (bn): BatchNorm2d(32, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  462.             (act): SiLU(inplace=True)
  463.           )
  464.           (conv2): BaseConv(
  465.             (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  466.             (bn): BatchNorm2d(32, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  467.             (act): SiLU(inplace=True)
  468.           )
  469.         )
  470.       )
  471.     )
  472.     (bu_conv2): BaseConv(
  473.       (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
  474.       (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  475.       (act): SiLU(inplace=True)
  476.     )
  477.     (C3_n3): CSPLayer(
  478.       (conv1): BaseConv(
  479.         (conv): Conv2d(128, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)
  480.         (bn): BatchNorm2d(80, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  481.         (act): SiLU(inplace=True)
  482.       )
  483.       (conv2): BaseConv(
  484.         (conv): Conv2d(128, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)
  485.         (bn): BatchNorm2d(80, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  486.         (act): SiLU(inplace=True)
  487.       )
  488.       (conv3): BaseConv(
  489.         (conv): Conv2d(160, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
  490.         (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  491.         (act): SiLU(inplace=True)
  492.       )
  493.       (m): Sequential(
  494.         (0): Bottleneck(
  495.           (conv1): BaseConv(
  496.             (conv): Conv2d(80, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)
  497.             (bn): BatchNorm2d(80, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  498.             (act): SiLU(inplace=True)
  499.           )
  500.           (conv2): BaseConv(
  501.             (conv): Conv2d(80, 80, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  502.             (bn): BatchNorm2d(80, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  503.             (act): SiLU(inplace=True)
  504.           )
  505.         )
  506.         (1): Bottleneck(
  507.           (conv1): BaseConv(
  508.             (conv): Conv2d(80, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)
  509.             (bn): BatchNorm2d(80, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  510.             (act): SiLU(inplace=True)
  511.           )
  512.           (conv2): BaseConv(
  513.             (conv): Conv2d(80, 80, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  514.             (bn): BatchNorm2d(80, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  515.             (act): SiLU(inplace=True)
  516.           )
  517.         )
  518.         (2): Bottleneck(
  519.           (conv1): BaseConv(
  520.             (conv): Conv2d(80, 80, kernel_size=(1, 1), stride=(1, 1), bias=False)
  521.             (bn): BatchNorm2d(80, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  522.             (act): SiLU(inplace=True)
  523.           )
  524.           (conv2): BaseConv(
  525.             (conv): Conv2d(80, 80, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  526.             (bn): BatchNorm2d(80, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  527.             (act): SiLU(inplace=True)
  528.           )
  529.         )
  530.       )
  531.     )
  532.     (bu_conv1): BaseConv(
  533.       (conv): Conv2d(160, 160, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
  534.       (bn): BatchNorm2d(160, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  535.       (act): SiLU(inplace=True)
  536.     )
  537.     (C3_n4): CSPLayer(
  538.       (conv1): BaseConv(
  539.         (conv): Conv2d(320, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
  540.         (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  541.         (act): SiLU(inplace=True)
  542.       )
  543.       (conv2): BaseConv(
  544.         (conv): Conv2d(320, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
  545.         (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  546.         (act): SiLU(inplace=True)
  547.       )
  548.       (conv3): BaseConv(
  549.         (conv): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
  550.         (bn): BatchNorm2d(384, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  551.         (act): SiLU(inplace=True)
  552.       )
  553.       (m): Sequential(
  554.         (0): Bottleneck(
  555.           (conv1): BaseConv(
  556.             (conv): Conv2d(192, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
  557.             (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  558.             (act): SiLU(inplace=True)
  559.           )
  560.           (conv2): BaseConv(
  561.             (conv): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  562.             (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  563.             (act): SiLU(inplace=True)
  564.           )
  565.         )
  566.         (1): Bottleneck(
  567.           (conv1): BaseConv(
  568.             (conv): Conv2d(192, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
  569.             (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  570.             (act): SiLU(inplace=True)
  571.           )
  572.           (conv2): BaseConv(
  573.             (conv): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  574.             (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  575.             (act): SiLU(inplace=True)
  576.           )
  577.         )
  578.         (2): Bottleneck(
  579.           (conv1): BaseConv(
  580.             (conv): Conv2d(192, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
  581.             (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  582.             (act): SiLU(inplace=True)
  583.           )
  584.           (conv2): BaseConv(
  585.             (conv): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  586.             (bn): BatchNorm2d(192, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  587.             (act): SiLU(inplace=True)
  588.           )
  589.         )
  590.       )
  591.     )
  592.   )
  593.   (head): YOLOXHeadFixed(
  594.     (cls_convs): ModuleList(
  595.       (0): Sequential(
  596.         (0): BaseConv(
  597.           (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  598.           (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  599.           (act): SiLU(inplace=True)
  600.         )
  601.         (1): BaseConv(
  602.           (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  603.           (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  604.           (act): SiLU(inplace=True)
  605.         )
  606.       )
  607.       (1): Sequential(
  608.         (0): BaseConv(
  609.           (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  610.           (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  611.           (act): SiLU(inplace=True)
  612.         )
  613.         (1): BaseConv(
  614.           (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  615.           (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  616.           (act): SiLU(inplace=True)
  617.         )
  618.       )
  619.       (2): Sequential(
  620.         (0): BaseConv(
  621.           (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  622.           (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  623.           (act): SiLU(inplace=True)
  624.         )
  625.         (1): BaseConv(
  626.           (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  627.           (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  628.           (act): SiLU(inplace=True)
  629.         )
  630.       )
  631.     )
  632.     (reg_convs): ModuleList(
  633.       (0): Sequential(
  634.         (0): BaseConv(
  635.           (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  636.           (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  637.           (act): SiLU(inplace=True)
  638.         )
  639.         (1): BaseConv(
  640.           (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  641.           (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  642.           (act): SiLU(inplace=True)
  643.         )
  644.       )
  645.       (1): Sequential(
  646.         (0): BaseConv(
  647.           (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  648.           (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  649.           (act): SiLU(inplace=True)
  650.         )
  651.         (1): BaseConv(
  652.           (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  653.           (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  654.           (act): SiLU(inplace=True)
  655.         )
  656.       )
  657.       (2): Sequential(
  658.         (0): BaseConv(
  659.           (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  660.           (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  661.           (act): SiLU(inplace=True)
  662.         )
  663.         (1): BaseConv(
  664.           (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
  665.           (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  666.           (act): SiLU(inplace=True)
  667.         )
  668.       )
  669.     )
  670.     (cls_preds): ModuleList(
  671.       (0): Conv2d(128, 7, kernel_size=(1, 1), stride=(1, 1))
  672.       (1): Conv2d(128, 7, kernel_size=(1, 1), stride=(1, 1))
  673.       (2): Conv2d(128, 7, kernel_size=(1, 1), stride=(1, 1))
  674.     )
  675.     (reg_preds): ModuleList(
  676.       (0): Conv2d(128, 4, kernel_size=(1, 1), stride=(1, 1))
  677.       (1): Conv2d(128, 4, kernel_size=(1, 1), stride=(1, 1))
  678.       (2): Conv2d(128, 4, kernel_size=(1, 1), stride=(1, 1))
  679.     )
  680.     (obj_preds): ModuleList(
  681.       (0): Conv2d(128, 1, kernel_size=(1, 1), stride=(1, 1))
  682.       (1): Conv2d(128, 1, kernel_size=(1, 1), stride=(1, 1))
  683.       (2): Conv2d(128, 1, kernel_size=(1, 1), stride=(1, 1))
  684.     )
  685.     (stems): ModuleList(
  686.       (0): BaseConv(
  687.         (conv): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
  688.         (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  689.         (act): SiLU(inplace=True)
  690.       )
  691.       (1): BaseConv(
  692.         (conv): Conv2d(160, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
  693.         (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  694.         (act): SiLU(inplace=True)
  695.       )
  696.       (2): BaseConv(
  697.         (conv): Conv2d(384, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
  698.         (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
  699.         (act): SiLU(inplace=True)
  700.       )
  701.     )
  702.     (l1_loss): L1Loss()
  703.     (bcewithlog_loss): BCEWithLogitsLoss()
  704.     (iou_loss): IOUloss()
  705.   )
  706. )
  707. 2024-02-18 22:18:08 | INFO     | yolox.core.trainer:199 - ---> start train epoch1
  708. 2024-02-18 22:18:15 | INFO     | yolox.core.trainer:257 - epoch: 1/300, iter: 10/250, mem: 2790Mb, iter_time: 0.753s, data_time: 0.002s, total_loss: 15.9, iou_loss: 4.3, l1_loss: 2.3, conf_loss: 8.0, cls_loss: 1.2, lr: 1.600e-07, size: 256, ETA: 15:41:22
  709. 2024-02-18 22:18:25 | INFO     | yolox.core.trainer:257 - epoch: 1/300, iter: 20/250, mem: 3853Mb, iter_time: 0.915s, data_time: 0.002s, total_loss: 20.4, iou_loss: 4.3, l1_loss: 2.7, conf_loss: 12.2, cls_loss: 1.1, lr: 6.400e-07, size: 384, ETA: 17:22:16
  710. 2024-02-18 22:18:35 | INFO     | yolox.core.trainer:257 - epoch: 1/300, iter: 30/250, mem: 3871Mb, iter_time: 1.053s, data_time: 0.002s, total_loss: 21.8, iou_loss: 4.2, l1_loss: 2.4, conf_loss: 14.0, cls_loss: 1.1, lr: 1.440e-06, size: 416, ETA: 18:53:27
  711. 2024-02-18 22:18:39 | INFO     | yolox.core.trainer:257 - epoch: 1/300, iter: 40/250, mem: 3871Mb, iter_time: 0.380s, data_time: 0.001s, total_loss: 15.2, iou_loss: 4.4, l1_loss: 2.3, conf_loss: 7.3, cls_loss: 1.2, lr: 2.560e-06, size: 256, ETA: 16:08:35
  712. 2024-02-18 22:18:45 | INFO     | yolox.core.trainer:257 - epoch: 1/300, iter: 50/250, mem: 3871Mb, iter_time: 0.576s, data_time: 0.002s, total_loss: 14.7, iou_loss: 4.2, l1_loss: 2.0, conf_loss: 7.3, cls_loss: 1.2, lr: 4.000e-06, size: 224, ETA: 15:18:46
  713. 2024-02-18 22:18:52 | INFO     | yolox.core.trainer:257 - epoch: 1/300, iter: 60/250, mem: 3871Mb, iter_time: 0.701s, data_time: 0.002s, total_loss: 20.0, iou_loss: 4.4, l1_loss: 2.8, conf_loss: 11.8, cls_loss: 1.1, lr: 5.760e-06, size: 416, ETA: 15:11:29
  714. 2024-02-18 22:18:59 | INFO     | yolox.core.trainer:257 - epoch: 1/300, iter: 70/250, mem: 3871Mb, iter_time: 0.689s, data_time: 0.002s, total_loss: 25.5, iou_loss: 4.3, l1_loss: 2.8, conf_loss: 17.3, cls_loss: 1.1, lr: 7.840e-06, size: 416, ETA: 15:04:08
  715. 2024-02-18 22:19:04 | INFO     | yolox.core.trainer:257 - epoch: 1/300, iter: 80/250, mem: 3871Mb, iter_time: 0.532s, data_time: 0.001s, total_loss: 14.0, iou_loss: 4.4, l1_loss: 2.1, conf_loss: 6.4, cls_loss: 1.2, lr: 1.024e-05, size: 192, ETA: 14:34:04
  716. 2024-02-18 22:19:12 | INFO     | yolox.core.trainer:257 - epoch: 1/300, iter: 90/250, mem: 3871Mb, iter_time: 0.847s, data_time: 0.002s, total_loss: 19.2, iou_loss: 4.5, l1_loss: 2.5, conf_loss: 11.2, cls_loss: 1.1, lr: 1.296e-05, size: 320, ETA: 14:54:16
  717. 2024-02-18 22:19:18 | INFO     | yolox.core.trainer:257 - epoch: 1/300, iter: 100/250, mem: 3871Mb, iter_time: 0.524s, data_time: 0.002s, total_loss: 16.2, iou_loss: 4.1, l1_loss: 2.2, conf_loss: 8.7, cls_loss: 1.3, lr: 1.600e-05, size: 320, ETA: 14:30:13
  718. 2024-02-18 22:19:23 | INFO     | yolox.core.trainer:257 - epoch: 1/300, iter: 110/250, mem: 3871Mb, iter_time: 0.519s, data_time: 0.001s, total_loss: 18.0, iou_loss: 4.3, l1_loss: 2.4, conf_loss: 10.2, cls_loss: 1.2, lr: 1.936e-05, size: 320, ETA: 14:09:50
  719. 2024-02-18 22:19:32 | INFO     | yolox.core.trainer:257 - epoch: 1/300, iter: 120/250, mem: 3871Mb, iter_time: 0.913s, data_time: 0.002s, total_loss: 21.2, iou_loss: 4.4, l1_loss: 2.7, conf_loss: 13.0, cls_loss: 1.0, lr: 2.304e-05, size: 352, ETA: 14:33:49
  720. 2024-02-18 22:19:35 | INFO     | yolox.core.trainer:257 - epoch: 1/300, iter: 130/250, mem: 3871Mb, iter_time: 0.337s, data_time: 0.001s, total_loss: 13.8, iou_loss: 4.2, l1_loss: 2.1, conf_loss: 6.2, cls_loss: 1.3, lr: 2.704e-05, size: 192, ETA: 13:58:51
  721. 2024-02-18 22:19:39 | INFO     | yolox.core.trainer:257 - epoch: 1/300, iter: 140/250, mem: 3871Mb, iter_time: 0.395s, data_time: 0.002s, total_loss: 13.4, iou_loss: 4.1, l1_loss: 2.1, conf_loss: 5.8, cls_loss: 1.4, lr: 3.136e-05, size: 160, ETA: 13:34:01
  722. 2024-02-18 22:19:45 | INFO     | yolox.core.trainer:257 - epoch: 1/300, iter: 150/250, mem: 3871Mb, iter_time: 0.584s, data_time: 0.175s, total_loss: 15.0, iou_loss: 4.1, l1_loss: 2.1, conf_loss: 7.5, cls_loss: 1.3, lr: 3.600e-05, size: 256, ETA: 13:28:14
  723. 2024-02-18 22:19:51 | INFO     | yolox.core.trainer:257 - epoch: 1/300, iter: 160/250, mem: 3871Mb, iter_time: 0.584s, data_time: 0.210s, total_loss: 14.3, iou_loss: 4.1, l1_loss: 2.4, conf_loss: 6.5, cls_loss: 1.3, lr: 4.096e-05, size: 224, ETA: 13:23:07
  724. 2024-02-18 22:19:59 | INFO     | yolox.core.trainer:257 - epoch: 1/300, iter: 170/250, mem: 3871Mb, iter_time: 0.765s, data_time: 0.349s, total_loss: 14.7, iou_loss: 4.2, l1_loss: 2.3, conf_loss: 6.8, cls_loss: 1.3, lr: 4.624e-05, size: 256, ETA: 13:31:53
  725. 2024-02-18 22:20:07 | INFO     | yolox.core.trainer:257 - epoch: 1/300, iter: 180/250, mem: 3871Mb, iter_time: 0.790s, data_time: 0.045s, total_loss: 14.5, iou_loss: 3.7, l1_loss: 2.2, conf_loss: 7.1, cls_loss: 1.5, lr: 5.184e-05, size: 288, ETA: 13:41:26
  726. 2024-02-18 22:20:14 | INFO     | yolox.core.trainer:257 - epoch: 1/300, iter: 190/250, mem: 3871Mb, iter_time: 0.734s, data_time: 0.019s, total_loss: 16.4, iou_loss: 3.8, l1_loss: 2.7, conf_loss: 8.4, cls_loss: 1.5, lr: 5.776e-05, size: 416, ETA: 13:46:15
  727. 2024-02-18 22:20:21 | INFO     | yolox.core.trainer:257 - epoch: 1/300, iter: 200/250, mem: 3871Mb, iter_time: 0.658s, data_time: 0.348s, total_loss: 13.1, iou_loss: 3.6, l1_loss: 2.2, conf_loss: 5.7, cls_loss: 1.5, lr: 6.400e-05, size: 192, ETA: 13:45:51
  728. 2024-02-18 22:20:28 | INFO     | yolox.core.trainer:257 - epoch: 1/300, iter: 210/250, mem: 3871Mb, iter_time: 0.732s, data_time: 0.136s, total_loss: 15.4, iou_loss: 3.6, l1_loss: 2.6, conf_loss: 7.7, cls_loss: 1.5, lr: 7.056e-05, size: 384, ETA: 13:49:53
  729. 2024-02-18 22:20:33 | INFO     | yolox.core.trainer:257 - epoch: 1/300, iter: 220/250, mem: 3871Mb, iter_time: 0.535s, data_time: 0.246s, total_loss: 13.0, iou_loss: 3.8, l1_loss: 2.1, conf_loss: 5.7, cls_loss: 1.5, lr: 7.744e-05, size: 192, ETA: 13:42:23
  730. 2024-02-18 22:20:41 | INFO     | yolox.core.trainer:257 - epoch: 1/300, iter: 230/250, mem: 3871Mb, iter_time: 0.789s, data_time: 0.484s, total_loss: 12.2, iou_loss: 3.8, l1_loss: 2.1, conf_loss: 4.9, cls_loss: 1.4, lr: 8.464e-05, size: 160, ETA: 13:49:15
  731. 2024-02-18 22:20:46 | INFO     | yolox.core.trainer:257 - epoch: 1/300, iter: 240/250, mem: 3871Mb, iter_time: 0.481s, data_time: 0.085s, total_loss: 13.3, iou_loss: 3.5, l1_loss: 2.3, conf_loss: 5.9, cls_loss: 1.6, lr: 9.216e-05, size: 256, ETA: 13:39:34
  732. 2024-02-18 22:20:54 | INFO     | yolox.core.trainer:257 - epoch: 1/300, iter: 250/250, mem: 3871Mb, iter_time: 0.793s, data_time: 0.375s, total_loss: 12.8, iou_loss: 3.5, l1_loss: 2.4, conf_loss: 5.5, cls_loss: 1.4, lr: 1.000e-04, size: 256, ETA: 13:46:12
  733. 2024-02-18 22:20:54 | INFO     | yolox.core.trainer:359 - Save weights to ./YOLOX_outputs/yolox_regnet
  734. 2024-02-18 22:20:55 | INFO     | yolox.core.trainer:199 - ---> start train epoch2
  735. 2024-02-18 22:21:02 | INFO     | yolox.core.trainer:257 - epoch: 2/300, iter: 10/250, mem: 3871Mb, iter_time: 0.654s, data_time: 0.285s, total_loss: 12.2, iou_loss: 4.0, l1_loss: 2.5, conf_loss: 4.6, cls_loss: 1.2, lr: 1.082e-04, size: 96, ETA: 13:45:39
  736. 2024-02-18 22:21:08 | INFO     | yolox.core.trainer:257 - epoch: 2/300, iter: 20/250, mem: 3871Mb, iter_time: 0.663s, data_time: 0.098s, total_loss: 14.2, iou_loss: 3.4, l1_loss: 2.4, conf_loss: 6.9, cls_loss: 1.5, lr: 1.166e-04, size: 320, ETA: 13:45:32
  737. 2024-02-18 22:21:17 | INFO     | yolox.core.trainer:257 - epoch: 2/300, iter: 30/250, mem: 3871Mb, iter_time: 0.885s, data_time: 0.272s, total_loss: 13.8, iou_loss: 3.2, l1_loss: 2.5, conf_loss: 6.8, cls_loss: 1.3, lr: 1.254e-04, size: 352, ETA: 13:55:18
  738. 2024-02-18 22:21:23 | INFO     | yolox.core.trainer:257 - epoch: 2/300, iter: 40/250, mem: 3871Mb, iter_time: 0.629s, data_time: 0.245s, total_loss: 12.3, iou_loss: 3.3, l1_loss: 2.3, conf_loss: 5.3, cls_loss: 1.4, lr: 1.346e-04, size: 256, ETA: 13:53:24
  739. 2024-02-18 22:21:30 | INFO     | yolox.core.trainer:257 - epoch: 2/300, iter: 50/250, mem: 3871Mb, iter_time: 0.627s, data_time: 0.188s, total_loss: 12.2, iou_loss: 3.1, l1_loss: 2.4, conf_loss: 5.3, cls_loss: 1.3, lr: 1.440e-04, size: 288, ETA: 13:51:31
  740. 2024-02-18 22:21:39 | INFO     | yolox.core.trainer:257 - epoch: 2/300, iter: 60/250, mem: 3871Mb, iter_time: 0.933s, data_time: 0.552s, total_loss: 11.7, iou_loss: 3.3, l1_loss: 2.1, conf_loss: 4.8, cls_loss: 1.5, lr: 1.538e-04, size: 192, ETA: 14:02:04
  741. 2024-02-18 22:21:44 | INFO     | yolox.core.trainer:257 - epoch: 2/300, iter: 70/250, mem: 3871Mb, iter_time: 0.462s, data_time: 0.111s, total_loss: 11.4, iou_loss: 3.3, l1_loss: 2.2, conf_loss: 4.7, cls_loss: 1.3, lr: 1.638e-04, size: 224, ETA: 13:53:36
  742. 2024-02-18 22:21:52 | INFO     | yolox.core.trainer:257 - epoch: 2/300, iter: 80/250, mem: 3871Mb, iter_time: 0.811s, data_time: 0.379s, total_loss: 12.1, iou_loss: 3.2, l1_loss: 2.2, conf_loss: 5.4, cls_loss: 1.3, lr: 1.742e-04, size: 256, ETA: 13:58:49
  743. 2024-02-18 22:22:00 | INFO     | yolox.core.trainer:257 - epoch: 2/300, iter: 90/250, mem: 3871Mb, iter_time: 0.797s, data_time: 0.211s, total_loss: 12.9, iou_loss: 3.2, l1_loss: 2.5, conf_loss: 5.9, cls_loss: 1.4, lr: 1.850e-04, size: 352, ETA: 14:03:13
  744. 2024-02-18 22:22:05 | INFO     | yolox.core.trainer:257 - epoch: 2/300, iter: 100/250, mem: 3871Mb, iter_time: 0.501s, data_time: 0.088s, total_loss: 11.2, iou_loss: 2.9, l1_loss: 2.2, conf_loss: 4.7, cls_loss: 1.4, lr: 1.960e-04, size: 256, ETA: 13:56:49
  745. 2024-02-18 22:22:14 | INFO     | yolox.core.trainer:257 - epoch: 2/300, iter: 110/250, mem: 3871Mb, iter_time: 0.917s, data_time: 0.264s, total_loss: 13.5, iou_loss: 2.9, l1_loss: 2.5, conf_loss: 6.5, cls_loss: 1.5, lr: 2.074e-04, size: 384, ETA: 14:05:08
  746. 2024-02-18 22:22:22 | INFO     | yolox.core.trainer:257 - epoch: 2/300, iter: 120/250, mem: 3871Mb, iter_time: 0.765s, data_time: 0.001s, total_loss: 12.5, iou_loss: 2.7, l1_loss: 2.4, conf_loss: 5.9, cls_loss: 1.4, lr: 2.190e-04, size: 416, ETA: 14:07:54
  747. 2024-02-18 22:22:27 | INFO     | yolox.core.trainer:257 - epoch: 2/300, iter: 130/250, mem: 3871Mb, iter_time: 0.517s, data_time: 0.114s, total_loss: 11.2, iou_loss: 3.3, l1_loss: 1.9, conf_loss: 4.6, cls_loss: 1.3, lr: 2.310e-04, size: 128, ETA: 14:02:24
  748. 2024-02-18 22:22:36 | INFO     | yolox.core.trainer:257 - epoch: 2/300, iter: 140/250, mem: 3871Mb, iter_time: 0.876s, data_time: 0.542s, total_loss: 10.8, iou_loss: 3.1, l1_loss: 1.9, conf_loss: 4.4, cls_loss: 1.3, lr: 2.434e-04, size: 160, ETA: 14:08:36
  749. 2024-02-18 22:22:41 | INFO     | yolox.core.trainer:257 - epoch: 2/300, iter: 150/250, mem: 3871Mb, iter_time: 0.518s, data_time: 0.126s, total_loss: 10.9, iou_loss: 3.0, l1_loss: 2.2, conf_loss: 4.4, cls_loss: 1.3, lr: 2.560e-04, size: 224, ETA: 14:03:23
  750. 2024-02-18 22:22:50 | INFO     | yolox.core.trainer:257 - epoch: 2/300, iter: 160/250, mem: 3871Mb, iter_time: 0.977s, data_time: 0.239s, total_loss: 12.5, iou_loss: 2.9, l1_loss: 2.4, conf_loss: 5.9, cls_loss: 1.3, lr: 2.690e-04, size: 416, ETA: 14:12:20
  751. 2024-02-18 22:22:57 | INFO     | yolox.core.trainer:257 - epoch: 2/300, iter: 170/250, mem: 3871Mb, iter_time: 0.608s, data_time: 0.145s, total_loss: 11.6, iou_loss: 2.8, l1_loss: 2.3, conf_loss: 5.2, cls_loss: 1.4, lr: 2.822e-04, size: 288, ETA: 14:09:56
  752. 2024-02-18 22:23:04 | INFO     | yolox.core.trainer:257 - epoch: 2/300, iter: 180/250, mem: 3871Mb, iter_time: 0.713s, data_time: 0.133s, total_loss: 11.8, iou_loss: 2.8, l1_loss: 2.5, conf_loss: 5.3, cls_loss: 1.3, lr: 2.958e-04, size: 352, ETA: 14:10:39
  753. 2024-02-18 22:23:11 | INFO     | yolox.core.trainer:257 - epoch: 2/300, iter: 190/250, mem: 3871Mb, iter_time: 0.691s, data_time: 0.401s, total_loss: 10.7, iou_loss: 3.0, l1_loss: 1.9, conf_loss: 4.4, cls_loss: 1.3, lr: 3.098e-04, size: 160, ETA: 14:10:43
  754. 2024-02-18 22:23:17 | INFO     | yolox.core.trainer:257 - epoch: 2/300, iter: 200/250, mem: 3871Mb, iter_time: 0.610s, data_time: 0.001s, total_loss: 11.8, iou_loss: 2.8, l1_loss: 2.4, conf_loss: 5.3, cls_loss: 1.3, lr: 3.240e-04, size: 384, ETA: 14:08:32
  755. 2024-02-18 22:23:23 | INFO     | yolox.core.trainer:257 - epoch: 2/300, iter: 210/250, mem: 3871Mb, iter_time: 0.654s, data_time: 0.248s, total_loss: 10.7, iou_loss: 2.8, l1_loss: 2.1, conf_loss: 4.5, cls_loss: 1.3, lr: 3.386e-04, size: 256, ETA: 14:07:39
  756. 2024-02-18 22:23:32 | INFO     | yolox.core.trainer:257 - epoch: 2/300, iter: 220/250, mem: 3871Mb, iter_time: 0.848s, data_time: 0.508s, total_loss: 10.6, iou_loss: 3.2, l1_loss: 2.0, conf_loss: 4.2, cls_loss: 1.3, lr: 3.534e-04, size: 128, ETA: 14:11:55
  757. 2024-02-18 22:23:39 | INFO     | yolox.core.trainer:257 - epoch: 2/300, iter: 230/250, mem: 3871Mb, iter_time: 0.738s, data_time: 0.008s, total_loss: 11.9, iou_loss: 2.7, l1_loss: 2.5, conf_loss: 5.5, cls_loss: 1.3, lr: 3.686e-04, size: 416, ETA: 14:13:09
  758. 2024-02-18 22:23:46 | INFO     | yolox.core.trainer:257 - epoch: 2/300, iter: 240/250, mem: 3871Mb, iter_time: 0.724s, data_time: 0.009s, total_loss: 11.9, iou_loss: 2.6, l1_loss: 2.3, conf_loss: 5.7, cls_loss: 1.4, lr: 3.842e-04, size: 416, ETA: 14:13:58
  759. 2024-02-18 22:23:51 | INFO     | yolox.core.trainer:257 - epoch: 2/300, iter: 250/250, mem: 3871Mb, iter_time: 0.462s, data_time: 0.179s, total_loss: 11.3, iou_loss: 3.4, l1_loss: 2.0, conf_loss: 4.5, cls_loss: 1.4, lr: 4.000e-04, size: 128, ETA: 14:08:15
  760. 2024-02-18 22:23:51 | INFO     | yolox.core.trainer:359 - Save weights to ./YOLOX_outputs/yolox_regnet
  761. 2024-02-18 22:23:52 | INFO     | yolox.core.trainer:199 - ---> start train epoch3
  762. 2024-02-18 22:23:56 | INFO     | yolox.core.trainer:257 - epoch: 3/300, iter: 10/250, mem: 3871Mb, iter_time: 0.373s, data_time: 0.087s, total_loss: 10.3, iou_loss: 3.2, l1_loss: 2.0, conf_loss: 3.9, cls_loss: 1.2, lr: 4.162e-04, size: 128, ETA: 14:00:35
  763. 2024-02-18 22:24:06 | INFO     | yolox.core.trainer:257 - epoch: 3/300, iter: 20/250, mem: 3871Mb, iter_time: 0.981s, data_time: 0.269s, total_loss: 12.2, iou_loss: 2.7, l1_loss: 2.4, conf_loss: 5.9, cls_loss: 1.2, lr: 4.326e-04, size: 416, ETA: 14:07:44
  764. 2024-02-18 22:24:12 | INFO     | yolox.core.trainer:257 - epoch: 3/300, iter: 30/250, mem: 3871Mb, iter_time: 0.623s, data_time: 0.001s, total_loss: 11.3, iou_loss: 2.6, l1_loss: 2.1, conf_loss: 5.2, cls_loss: 1.3, lr: 4.494e-04, size: 384, ETA: 14:06:13
  765. 2024-02-18 22:24:18 | INFO     | yolox.core.trainer:257 - epoch: 3/300, iter: 40/250, mem: 3871Mb, iter_time: 0.627s, data_time: 0.059s, total_loss: 11.5, iou_loss: 2.8, l1_loss: 2.2, conf_loss: 5.2, cls_loss: 1.2, lr: 4.666e-04, size: 352, ETA: 14:04:50
  766. 2024-02-18 22:24:25 | INFO     | yolox.core.trainer:257 - epoch: 3/300, iter: 50/250, mem: 3871Mb, iter_time: 0.676s, data_time: 0.324s, total_loss: 10.7, iou_loss: 2.8, l1_loss: 2.1, conf_loss: 4.6, cls_loss: 1.1, lr: 4.840e-04, size: 224, ETA: 14:04:36
  767. 2024-02-18 22:24:30 | INFO     | yolox.core.trainer:257 - epoch: 3/300, iter: 60/250, mem: 3871Mb, iter_time: 0.489s, data_time: 0.147s, total_loss: 9.8, iou_loss: 2.8, l1_loss: 2.0, conf_loss: 4.0, cls_loss: 1.1, lr: 5.018e-04, size: 224, ETA: 14:00:14
  768. 2024-02-18 22:24:36 | INFO     | yolox.core.trainer:257 - epoch: 3/300, iter: 70/250, mem: 3871Mb, iter_time: 0.643s, data_time: 0.373s, total_loss: 10.4, iou_loss: 3.3, l1_loss: 1.9, conf_loss: 3.9, cls_loss: 1.3, lr: 5.198e-04, size: 96, ETA: 13:59:23
  769. 2024-02-18 22:24:44 | INFO     | yolox.core.trainer:257 - epoch: 3/300, iter: 80/250, mem: 3871Mb, iter_time: 0.745s, data_time: 0.293s, total_loss: 10.7, iou_loss: 2.8, l1_loss: 2.0, conf_loss: 4.6, cls_loss: 1.3, lr: 5.382e-04, size: 288, ETA: 14:00:43
  770. 2024-02-18 22:24:51 | INFO     | yolox.core.trainer:257 - epoch: 3/300, iter: 90/250, mem: 3871Mb, iter_time: 0.773s, data_time: 0.054s, total_loss: 11.2, iou_loss: 2.5, l1_loss: 2.3, conf_loss: 5.2, cls_loss: 1.2, lr: 5.570e-04, size: 416, ETA: 14:02:37
  771. 2024-02-18 22:24:57 | INFO     | yolox.core.trainer:257 - epoch: 3/300, iter: 100/250, mem: 3871Mb, iter_time: 0.546s, data_time: 0.200s, total_loss: 10.1, iou_loss: 2.8, l1_loss: 2.1, conf_loss: 4.2, cls_loss: 1.1, lr: 5.760e-04, size: 224, ETA: 13:59:45
  772. 2024-02-18 22:25:02 | INFO     | yolox.core.trainer:257 - epoch: 3/300, iter: 110/250, mem: 3871Mb, iter_time: 0.494s, data_time: 0.240s, total_loss: 10.0, iou_loss: 3.2, l1_loss: 2.0, conf_loss: 3.8, cls_loss: 1.0, lr: 5.954e-04, size: 96, ETA: 13:55:55
  773. 2024-02-18 22:25:08 | INFO     | yolox.core.trainer:257 - epoch: 3/300, iter: 120/250, mem: 3871Mb, iter_time: 0.578s, data_time: 0.302s, total_loss: 9.2, iou_loss: 3.1, l1_loss: 1.8, conf_loss: 3.4, cls_loss: 1.0, lr: 6.150e-04, size: 96, ETA: 13:53:52
  774. 2024-02-18 22:25:16 | INFO     | yolox.core.trainer:257 - epoch: 3/300, iter: 130/250, mem: 3871Mb, iter_time: 0.869s, data_time: 0.417s, total_loss: 10.5, iou_loss: 2.7, l1_loss: 2.1, conf_loss: 4.5, cls_loss: 1.2, lr: 6.350e-04, size: 288, ETA: 13:57:37
  775. 2024-02-18 22:25:24 | INFO     | yolox.core.trainer:257 - epoch: 3/300, iter: 140/250, mem: 3871Mb, iter_time: 0.725s, data_time: 0.030s, total_loss: 11.2, iou_loss: 2.5, l1_loss: 2.2, conf_loss: 5.3, cls_loss: 1.1, lr: 6.554e-04, size: 416, ETA: 13:58:27
  776. 2024-02-18 22:25:30 | INFO     | yolox.core.trainer:257 - epoch: 3/300, iter: 150/250, mem: 3871Mb, iter_time: 0.627s, data_time: 0.031s, total_loss: 10.8, iou_loss: 2.5, l1_loss: 2.1, conf_loss: 4.9, cls_loss: 1.2, lr: 6.760e-04, size: 384, ETA: 13:57:24
  777. 2024-02-18 22:25:36 | INFO     | yolox.core.trainer:257 - epoch: 3/300, iter: 160/250, mem: 3871Mb, iter_time: 0.610s, data_time: 0.278s, total_loss: 10.0, iou_loss: 2.6, l1_loss: 2.0, conf_loss: 4.3, cls_loss: 1.1, lr: 6.970e-04, size: 224, ETA: 13:56:03
  778. 2024-02-18 22:25:40 | INFO     | yolox.core.trainer:257 - epoch: 3/300, iter: 170/250, mem: 3871Mb, iter_time: 0.397s, data_time: 0.133s, total_loss: 10.2, iou_loss: 3.1, l1_loss: 1.9, conf_loss: 3.9, cls_loss: 1.2, lr: 7.182e-04, size: 128, ETA: 13:50:48
  779. 2024-02-18 22:25:49 | INFO     | yolox.core.trainer:257 - epoch: 3/300, iter: 180/250, mem: 3871Mb, iter_time: 0.884s, data_time: 0.443s, total_loss: 10.3, iou_loss: 2.5, l1_loss: 1.9, conf_loss: 4.6, cls_loss: 1.3, lr: 7.398e-04, size: 288, ETA: 13:54:34
  780. 2024-02-18 22:25:54 | INFO     | yolox.core.trainer:257 - epoch: 3/300, iter: 190/250, mem: 3871Mb, iter_time: 0.544s, data_time: 0.292s, total_loss: 9.7, iou_loss: 2.9, l1_loss: 1.8, conf_loss: 3.9, cls_loss: 1.1, lr: 7.618e-04, size: 128, ETA: 13:52:07
  781. 2024-02-18 22:25:59 | INFO     | yolox.core.trainer:257 - epoch: 3/300, iter: 200/250, mem: 3871Mb, iter_time: 0.527s, data_time: 0.281s, total_loss: 10.1, iou_loss: 3.3, l1_loss: 1.9, conf_loss: 3.9, cls_loss: 1.0, lr: 7.840e-04, size: 96, ETA: 13:49:27
  782. 2024-02-18 22:26:07 | INFO     | yolox.core.trainer:257 - epoch: 3/300, iter: 210/250, mem: 3871Mb, iter_time: 0.780s, data_time: 0.450s, total_loss: 10.0, iou_loss: 2.7, l1_loss: 1.9, conf_loss: 4.2, cls_loss: 1.2, lr: 8.066e-04, size: 224, ETA: 13:51:15
  783. 2024-02-18 22:26:13 | INFO     | yolox.core.trainer:257 - epoch: 3/300, iter: 220/250, mem: 3871Mb, iter_time: 0.607s, data_time: 0.029s, total_loss: 10.7, iou_loss: 2.6, l1_loss: 2.0, conf_loss: 4.8, cls_loss: 1.3, lr: 8.294e-04, size: 352, ETA: 13:50:02
  784. 2024-02-18 22:26:21 | INFO     | yolox.core.trainer:257 - epoch: 3/300, iter: 230/250, mem: 3871Mb, iter_time: 0.735s, data_time: 0.108s, total_loss: 10.8, iou_loss: 2.5, l1_loss: 2.1, conf_loss: 4.9, cls_loss: 1.5, lr: 8.526e-04, size: 384, ETA: 13:51:01
  785. 2024-02-18 22:26:27 | INFO     | yolox.core.trainer:257 - epoch: 3/300, iter: 240/250, mem: 3871Mb, iter_time: 0.632s, data_time: 0.236s, total_loss: 9.6, iou_loss: 2.6, l1_loss: 2.0, conf_loss: 4.0, cls_loss: 1.1, lr: 8.762e-04, size: 256, ETA: 13:50:14
  786. 2024-02-18 22:26:32 | INFO     | yolox.core.trainer:257 - epoch: 3/300, iter: 250/250, mem: 3871Mb, iter_time: 0.467s, data_time: 0.077s, total_loss: 10.1, iou_loss: 2.6, l1_loss: 1.9, conf_loss: 4.4, cls_loss: 1.2, lr: 9.000e-04, size: 256, ETA: 13:46:45
  787. 2024-02-18 22:26:32 | INFO     | yolox.core.trainer:359 - Save weights to ./YOLOX_outputs/yolox_regnet
  788. 2024-02-18 22:26:33 | INFO     | yolox.core.trainer:199 - ---> start train epoch4
  789. 2024-02-18 22:26:40 | INFO     | yolox.core.trainer:257 - epoch: 4/300, iter: 10/250, mem: 3871Mb, iter_time: 0.750s, data_time: 0.157s, total_loss: 10.2, iou_loss: 2.4, l1_loss: 2.0, conf_loss: 4.5, cls_loss: 1.3, lr: 9.242e-04, size: 352, ETA: 13:47:59
  790. 2024-02-18 22:26:46 | INFO     | yolox.core.trainer:257 - epoch: 4/300, iter: 20/250, mem: 3871Mb, iter_time: 0.600s, data_time: 0.152s, total_loss: 9.8, iou_loss: 2.4, l1_loss: 2.0, conf_loss: 4.1, cls_loss: 1.2, lr: 9.486e-04, size: 288, ETA: 13:46:45
  791. 2024-02-18 22:26:51 | INFO     | yolox.core.trainer:257 - epoch: 4/300, iter: 30/250, mem: 3871Mb, iter_time: 0.513s, data_time: 0.209s, total_loss: 10.0, iou_loss: 2.9, l1_loss: 1.9, conf_loss: 3.8, cls_loss: 1.4, lr: 9.734e-04, size: 160, ETA: 13:44:11
  792. 2024-02-18 22:26:59 | INFO     | yolox.core.trainer:257 - epoch: 4/300, iter: 40/250, mem: 3871Mb, iter_time: 0.780s, data_time: 0.433s, total_loss: 9.4, iou_loss: 2.6, l1_loss: 1.8, conf_loss: 3.9, cls_loss: 1.1, lr: 9.986e-04, size: 224, ETA: 13:45:51
  793. 2024-02-18 22:27:04 | INFO     | yolox.core.trainer:257 - epoch: 4/300, iter: 50/250, mem: 3871Mb, iter_time: 0.516s, data_time: 0.191s, total_loss: 10.0, iou_loss: 2.8, l1_loss: 2.0, conf_loss: 4.0, cls_loss: 1.2, lr: 1.024e-03, size: 192, ETA: 13:43:24
  794. 2024-02-18 22:27:11 | INFO     | yolox.core.trainer:257 - epoch: 4/300, iter: 60/250, mem: 3871Mb, iter_time: 0.675s, data_time: 0.282s, total_loss: 9.8, iou_loss: 2.5, l1_loss: 1.9, conf_loss: 4.2, cls_loss: 1.2, lr: 1.050e-03, size: 256, ETA: 13:43:25
  795. 2024-02-18 22:27:18 | INFO     | yolox.core.trainer:257 - epoch: 4/300, iter: 70/250, mem: 3871Mb, iter_time: 0.731s, data_time: 0.216s, total_loss: 10.9, iou_loss: 2.6, l1_loss: 2.0, conf_loss: 4.9, cls_loss: 1.3, lr: 1.076e-03, size: 320, ETA: 13:44:17
  796. 2024-02-18 22:27:24 | INFO     | yolox.core.trainer:257 - epoch: 4/300, iter: 80/250, mem: 3871Mb, iter_time: 0.610s, data_time: 0.028s, total_loss: 9.9, iou_loss: 2.4, l1_loss: 1.8, conf_loss: 4.4, cls_loss: 1.3, lr: 1.102e-03, size: 352, ETA: 13:43:20
  797. 2024-02-18 22:27:31 | INFO     | yolox.core.trainer:257 - epoch: 4/300, iter: 90/250, mem: 3871Mb, iter_time: 0.649s, data_time: 0.302s, total_loss: 9.4, iou_loss: 2.5, l1_loss: 1.7, conf_loss: 3.8, cls_loss: 1.3, lr: 1.129e-03, size: 224, ETA: 13:42:58
  798. 2024-02-18 22:27:36 | INFO     | yolox.core.trainer:257 - epoch: 4/300, iter: 100/250, mem: 3871Mb, iter_time: 0.544s, data_time: 0.230s, total_loss: 8.9, iou_loss: 2.6, l1_loss: 1.7, conf_loss: 3.4, cls_loss: 1.1, lr: 1.156e-03, size: 192, ETA: 13:41:06
  799. 2024-02-18 22:27:43 | INFO     | yolox.core.trainer:257 - epoch: 4/300, iter: 110/250, mem: 3871Mb, iter_time: 0.660s, data_time: 0.203s, total_loss: 9.8, iou_loss: 2.5, l1_loss: 1.9, conf_loss: 4.1, cls_loss: 1.2, lr: 1.183e-03, size: 288, ETA: 13:40:55
  800. 2024-02-18 22:27:50 | INFO     | yolox.core.trainer:257 - epoch: 4/300, iter: 120/250, mem: 3871Mb, iter_time: 0.674s, data_time: 0.357s, total_loss: 9.5, iou_loss: 2.8, l1_loss: 1.8, conf_loss: 3.7, cls_loss: 1.2, lr: 1.211e-03, size: 192, ETA: 13:40:57
  801. 2024-02-18 22:27:56 | INFO     | yolox.core.trainer:257 - epoch: 4/300, iter: 130/250, mem: 3871Mb, iter_time: 0.620s, data_time: 0.265s, total_loss: 8.9, iou_loss: 2.7, l1_loss: 1.7, conf_loss: 3.4, cls_loss: 1.0, lr: 1.239e-03, size: 160, ETA: 13:40:13
  802. 2024-02-18 22:28:04 | INFO     | yolox.core.trainer:257 - epoch: 4/300, iter: 140/250, mem: 3871Mb, iter_time: 0.814s, data_time: 0.255s, total_loss: 9.4, iou_loss: 2.4, l1_loss: 1.7, conf_loss: 4.2, cls_loss: 1.1, lr: 1.267e-03, size: 320, ETA: 13:42:11
  803. 2024-02-18 22:28:11 | INFO     | yolox.core.trainer:257 - epoch: 4/300, iter: 150/250, mem: 3871Mb, iter_time: 0.730s, data_time: 0.406s, total_loss: 9.4, iou_loss: 3.0, l1_loss: 1.6, conf_loss: 3.7, cls_loss: 1.1, lr: 1.296e-03, size: 96, ETA: 13:42:57
  804. 2024-02-18 22:28:18 | INFO     | yolox.core.trainer:257 - epoch: 4/300, iter: 160/250, mem: 3871Mb, iter_time: 0.672s, data_time: 0.158s, total_loss: 10.2, iou_loss: 2.6, l1_loss: 2.0, conf_loss: 4.5, cls_loss: 1.2, lr: 1.325e-03, size: 288, ETA: 13:42:55
  805. 2024-02-18 22:28:27 | INFO     | yolox.core.trainer:257 - epoch: 4/300, iter: 170/250, mem: 3871Mb, iter_time: 0.850s, data_time: 0.508s, total_loss: 8.7, iou_loss: 2.6, l1_loss: 1.7, conf_loss: 3.4, cls_loss: 1.0, lr: 1.354e-03, size: 160, ETA: 13:45:15
  806. 2024-02-18 22:28:34 | INFO     | yolox.core.trainer:257 - epoch: 4/300, iter: 180/250, mem: 3871Mb, iter_time: 0.772s, data_time: 0.002s, total_loss: 10.1, iou_loss: 2.4, l1_loss: 1.9, conf_loss: 4.7, cls_loss: 1.2, lr: 1.384e-03, size: 416, ETA: 13:46:31
  807. 2024-02-18 22:28:42 | INFO     | yolox.core.trainer:257 - epoch: 4/300, iter: 190/250, mem: 3871Mb, iter_time: 0.788s, data_time: 0.119s, total_loss: 11.0, iou_loss: 2.5, l1_loss: 2.0, conf_loss: 5.4, cls_loss: 1.2, lr: 1.414e-03, size: 384, ETA: 13:47:58
  808. 2024-02-18 22:28:49 | INFO     | yolox.core.trainer:257 - epoch: 4/300, iter: 200/250, mem: 3871Mb, iter_time: 0.714s, data_time: 0.160s, total_loss: 9.8, iou_loss: 2.5, l1_loss: 1.8, conf_loss: 4.2, cls_loss: 1.3, lr: 1.444e-03, size: 320, ETA: 13:48:25
  809. 2024-02-18 22:28:56 | INFO     | yolox.core.trainer:257 - epoch: 4/300, iter: 210/250, mem: 3871Mb, iter_time: 0.671s, data_time: 0.121s, total_loss: 9.3, iou_loss: 2.3, l1_loss: 1.8, conf_loss: 4.1, cls_loss: 1.1, lr: 1.475e-03, size: 320, ETA: 13:48:18
  810. 2024-02-18 22:29:03 | INFO     | yolox.core.trainer:257 - epoch: 4/300, iter: 220/250, mem: 3871Mb, iter_time: 0.722s, data_time: 0.362s, total_loss: 8.8, iou_loss: 2.7, l1_loss: 1.7, conf_loss: 3.3, cls_loss: 1.1, lr: 1.505e-03, size: 160, ETA: 13:48:50
  811. 2024-02-18 22:29:11 | INFO     | yolox.core.trainer:257 - epoch: 4/300, iter: 230/250, mem: 3871Mb, iter_time: 0.756s, data_time: 0.362s, total_loss: 9.4, iou_loss: 2.4, l1_loss: 1.7, conf_loss: 3.9, cls_loss: 1.3, lr: 1.537e-03, size: 224, ETA: 13:49:47
  812. 2024-02-18 22:29:16 | INFO     | yolox.core.trainer:257 - epoch: 4/300, iter: 240/250, mem: 3871Mb, iter_time: 0.528s, data_time: 0.180s, total_loss: 10.5, iou_loss: 2.8, l1_loss: 2.0, conf_loss: 4.5, cls_loss: 1.3, lr: 1.568e-03, size: 192, ETA: 13:47:52
  813. 2024-02-18 22:29:25 | INFO     | yolox.core.trainer:257 - epoch: 4/300, iter: 250/250, mem: 3871Mb, iter_time: 0.873s, data_time: 0.450s, total_loss: 9.1, iou_loss: 2.4, l1_loss: 1.8, conf_loss: 3.8, cls_loss: 1.2, lr: 1.600e-03, size: 256, ETA: 13:50:15
  814. 2024-02-18 22:29:25 | INFO     | yolox.core.trainer:359 - Save weights to ./YOLOX_outputs/yolox_regnet
  815. 2024-02-18 22:29:26 | INFO     | yolox.core.trainer:199 - ---> start train epoch5
  816. 2024-02-18 22:29:32 | INFO     | yolox.core.trainer:257 - epoch: 5/300, iter: 10/250, mem: 3871Mb, iter_time: 0.572s, data_time: 0.010s, total_loss: 9.3, iou_loss: 2.3, l1_loss: 1.8, conf_loss: 4.1, cls_loss: 1.1, lr: 1.632e-03, size: 352, ETA: 13:48:53
  817. 2024-02-18 22:29:37 | INFO     | yolox.core.trainer:257 - epoch: 5/300, iter: 20/250, mem: 3871Mb, iter_time: 0.533s, data_time: 0.236s, total_loss: 9.4, iou_loss: 2.7, l1_loss: 1.8, conf_loss: 3.8, cls_loss: 1.1, lr: 1.665e-03, size: 192, ETA: 13:47:05
  818. 2024-02-18 22:29:45 | INFO     | yolox.core.trainer:257 - epoch: 5/300, iter: 30/250, mem: 3871Mb, iter_time: 0.762s, data_time: 0.362s, total_loss: 9.3, iou_loss: 2.5, l1_loss: 1.8, conf_loss: 3.8, cls_loss: 1.2, lr: 1.697e-03, size: 256, ETA: 13:48:04
  819. 2024-02-18 22:29:51 | INFO     | yolox.core.trainer:257 - epoch: 5/300, iter: 40/250, mem: 3871Mb, iter_time: 0.600s, data_time: 0.270s, total_loss: 8.6, iou_loss: 2.4, l1_loss: 1.6, conf_loss: 3.4, cls_loss: 1.2, lr: 1.731e-03, size: 192, ETA: 13:47:06
  820. 2024-02-18 22:29:58 | INFO     | yolox.core.trainer:257 - epoch: 5/300, iter: 50/250, mem: 3871Mb, iter_time: 0.748s, data_time: 0.214s, total_loss: 9.1, iou_loss: 2.3, l1_loss: 1.7, conf_loss: 4.1, cls_loss: 1.1, lr: 1.764e-03, size: 320, ETA: 13:47:54
  821. 2024-02-18 22:30:05 | INFO     | yolox.core.trainer:257 - epoch: 5/300, iter: 60/250, mem: 3871Mb, iter_time: 0.659s, data_time: 0.131s, total_loss: 9.2, iou_loss: 2.4, l1_loss: 1.8, conf_loss: 3.9, cls_loss: 1.1, lr: 1.798e-03, size: 320, ETA: 13:47:38
  822. 2024-02-18 22:30:13 | INFO     | yolox.core.trainer:257 - epoch: 5/300, iter: 70/250, mem: 3871Mb, iter_time: 0.779s, data_time: 0.144s, total_loss: 9.2, iou_loss: 2.2, l1_loss: 1.8, conf_loss: 4.1, cls_loss: 1.2, lr: 1.832e-03, size: 384, ETA: 13:48:46
  823. 2024-02-18 22:30:20 | INFO     | yolox.core.trainer:257 - epoch: 5/300, iter: 80/250, mem: 3871Mb, iter_time: 0.715s, data_time: 0.300s, total_loss: 8.8, iou_loss: 2.4, l1_loss: 1.6, conf_loss: 3.8, cls_loss: 1.1, lr: 1.866e-03, size: 256, ETA: 13:49:09
  824. 2024-02-18 22:30:26 | INFO     | yolox.core.trainer:257 - epoch: 5/300, iter: 90/250, mem: 3871Mb, iter_time: 0.601s, data_time: 0.307s, total_loss: 9.2, iou_loss: 3.0, l1_loss: 1.7, conf_loss: 3.4, cls_loss: 1.0, lr: 1.901e-03, size: 96, ETA: 13:48:13
  825. 2024-02-18 22:30:34 | INFO     | yolox.core.trainer:257 - epoch: 5/300, iter: 100/250, mem: 3871Mb, iter_time: 0.812s, data_time: 0.268s, total_loss: 9.7, iou_loss: 2.5, l1_loss: 1.7, conf_loss: 4.2, cls_loss: 1.2, lr: 1.936e-03, size: 288, ETA: 13:49:40
  826. 2024-02-18 22:30:40 | INFO     | yolox.core.trainer:257 - epoch: 5/300, iter: 110/250, mem: 3871Mb, iter_time: 0.636s, data_time: 0.106s, total_loss: 8.7, iou_loss: 2.2, l1_loss: 1.6, conf_loss: 3.9, cls_loss: 1.1, lr: 1.971e-03, size: 320, ETA: 13:49:08
  827. 2024-02-18 22:30:47 | INFO     | yolox.core.trainer:257 - epoch: 5/300, iter: 120/250, mem: 3871Mb, iter_time: 0.703s, data_time: 0.380s, total_loss: 8.6, iou_loss: 2.6, l1_loss: 1.5, conf_loss: 3.3, cls_loss: 1.1, lr: 2.007e-03, size: 128, ETA: 13:49:21
  828. 2024-02-18 22:30:55 | INFO     | yolox.core.trainer:257 - epoch: 5/300, iter: 130/250, mem: 3871Mb, iter_time: 0.801s, data_time: 0.358s, total_loss: 8.9, iou_loss: 2.3, l1_loss: 1.8, conf_loss: 3.8, cls_loss: 1.0, lr: 2.043e-03, size: 256, ETA: 13:50:37
  829. 2024-02-18 22:31:02 | INFO     | yolox.core.trainer:257 - epoch: 5/300, iter: 140/250, mem: 3871Mb, iter_time: 0.640s, data_time: 0.049s, total_loss: 9.4, iou_loss: 2.2, l1_loss: 1.7, conf_loss: 4.5, cls_loss: 1.1, lr: 2.079e-03, size: 352, ETA: 13:50:08
  830. 2024-02-18 22:31:09 | INFO     | yolox.core.trainer:257 - epoch: 5/300, iter: 150/250, mem: 3871Mb, iter_time: 0.699s, data_time: 0.213s, total_loss: 9.1, iou_loss: 2.4, l1_loss: 1.6, conf_loss: 3.9, cls_loss: 1.3, lr: 2.116e-03, size: 288, ETA: 13:50:17
  831. 2024-02-18 22:31:17 | INFO     | yolox.core.trainer:257 - epoch: 5/300, iter: 160/250, mem: 3871Mb, iter_time: 0.813s, data_time: 0.327s, total_loss: 8.6, iou_loss: 2.4, l1_loss: 1.6, conf_loss: 3.6, cls_loss: 1.0, lr: 2.153e-03, size: 288, ETA: 13:51:39
  832. 2024-02-18 22:31:23 | INFO     | yolox.core.trainer:257 - epoch: 5/300, iter: 170/250, mem: 3871Mb, iter_time: 0.604s, data_time: 0.129s, total_loss: 9.2, iou_loss: 2.4, l1_loss: 1.7, conf_loss: 3.9, cls_loss: 1.3, lr: 2.190e-03, size: 288, ETA: 13:50:47
  833. 2024-02-18 22:31:30 | INFO     | yolox.core.trainer:257 - epoch: 5/300, iter: 180/250, mem: 3871Mb, iter_time: 0.739s, data_time: 0.327s, total_loss: 8.3, iou_loss: 2.5, l1_loss: 1.4, conf_loss: 3.3, cls_loss: 1.1, lr: 2.228e-03, size: 192, ETA: 13:51:20
  834. 2024-02-18 22:31:37 | INFO     | yolox.core.trainer:257 - epoch: 5/300, iter: 190/250, mem: 3871Mb, iter_time: 0.708s, data_time: 0.343s, total_loss: 8.4, iou_loss: 2.7, l1_loss: 1.5, conf_loss: 3.1, cls_loss: 1.1, lr: 2.266e-03, size: 160, ETA: 13:51:33
  835. 2024-02-18 22:31:48 | INFO     | yolox.core.trainer:257 - epoch: 5/300, iter: 200/250, mem: 3871Mb, iter_time: 1.073s, data_time: 0.322s, total_loss: 9.3, iou_loss: 2.3, l1_loss: 1.6, conf_loss: 4.4, cls_loss: 1.0, lr: 2.304e-03, size: 416, ETA: 13:55:30
  836. 2024-02-18 22:31:54 | INFO     | yolox.core.trainer:257 - epoch: 5/300, iter: 210/250, mem: 3871Mb, iter_time: 0.635s, data_time: 0.049s, total_loss: 8.8, iou_loss: 2.2, l1_loss: 1.7, conf_loss: 3.8, cls_loss: 1.2, lr: 2.343e-03, size: 352, ETA: 13:54:57
  837. 2024-02-18 22:32:00 | INFO     | yolox.core.trainer:257 - epoch: 5/300, iter: 220/250, mem: 3871Mb, iter_time: 0.591s, data_time: 0.002s, total_loss: 9.2, iou_loss: 2.4, l1_loss: 1.6, conf_loss: 4.0, cls_loss: 1.2, lr: 2.381e-03, size: 352, ETA: 13:53:57
  838. 2024-02-18 22:32:08 | INFO     | yolox.core.trainer:257 - epoch: 5/300, iter: 230/250, mem: 3871Mb, iter_time: 0.763s, data_time: 0.132s, total_loss: 9.1, iou_loss: 2.3, l1_loss: 1.7, conf_loss: 3.9, cls_loss: 1.2, lr: 2.421e-03, size: 384, ETA: 13:54:41
  839. 2024-02-18 22:32:17 | INFO     | yolox.core.trainer:257 - epoch: 5/300, iter: 240/250, mem: 3871Mb, iter_time: 0.863s, data_time: 0.220s, total_loss: 9.2, iou_loss: 2.2, l1_loss: 1.6, conf_loss: 4.2, cls_loss: 1.2, lr: 2.460e-03, size: 352, ETA: 13:56:23
  840. 2024-02-18 22:32:22 | INFO     | yolox.core.trainer:257 - epoch: 5/300, iter: 250/250, mem: 3871Mb, iter_time: 0.538s, data_time: 0.220s, total_loss: 8.5, iou_loss: 2.7, l1_loss: 1.5, conf_loss: 3.3, cls_loss: 1.1, lr: 2.500e-03, size: 128, ETA: 13:54:53
  841. 2024-02-18 22:32:22 | INFO     | yolox.core.trainer:359 - Save weights to ./YOLOX_outputs/yolox_regnet
  842. 2024-02-18 22:32:23 | INFO     | yolox.core.trainer:199 - ---> start train epoch6
  843. 2024-02-18 22:32:29 | INFO     | yolox.core.trainer:257 - epoch: 6/300, iter: 10/250, mem: 3871Mb, iter_time: 0.594s, data_time: 0.185s, total_loss: 8.9, iou_loss: 2.6, l1_loss: 1.6, conf_loss: 3.6, cls_loss: 1.2, lr: 2.500e-03, size: 224, ETA: 13:53:56
  844. 2024-02-18 22:32:35 | INFO     | yolox.core.trainer:257 - epoch: 6/300, iter: 20/250, mem: 3871Mb, iter_time: 0.615s, data_time: 0.195s, total_loss: 8.9, iou_loss: 2.4, l1_loss: 1.7, conf_loss: 3.7, cls_loss: 1.1, lr: 2.500e-03, size: 256, ETA: 13:53:12
  845. 2024-02-18 22:32:43 | INFO     | yolox.core.trainer:257 - epoch: 6/300, iter: 30/250, mem: 3871Mb, iter_time: 0.797s, data_time: 0.404s, total_loss: 8.4, iou_loss: 2.4, l1_loss: 1.4, conf_loss: 3.6, cls_loss: 1.0, lr: 2.500e-03, size: 224, ETA: 13:54:14
  846. 2024-02-18 22:32:52 | INFO     | yolox.core.trainer:257 - epoch: 6/300, iter: 40/250, mem: 3871Mb, iter_time: 0.857s, data_time: 0.243s, total_loss: 8.5, iou_loss: 2.1, l1_loss: 1.6, conf_loss: 3.7, cls_loss: 1.1, lr: 2.500e-03, size: 352, ETA: 13:55:49
  847. 2024-02-18 22:32:57 | INFO     | yolox.core.trainer:257 - epoch: 6/300, iter: 50/250, mem: 3871Mb, iter_time: 0.518s, data_time: 0.100s, total_loss: 8.9, iou_loss: 2.4, l1_loss: 1.6, conf_loss: 3.7, cls_loss: 1.2, lr: 2.500e-03, size: 256, ETA: 13:54:09
  848. 2024-02-18 22:33:03 | INFO     | yolox.core.trainer:257 - epoch: 6/300, iter: 60/250, mem: 3871Mb, iter_time: 0.620s, data_time: 0.303s, total_loss: 8.1, iou_loss: 2.6, l1_loss: 1.4, conf_loss: 3.1, cls_loss: 1.0, lr: 2.500e-03, size: 128, ETA: 13:53:30
  849. 2024-02-18 22:33:13 | INFO     | yolox.core.trainer:257 - epoch: 6/300, iter: 70/250, mem: 3871Mb, iter_time: 0.993s, data_time: 0.257s, total_loss: 9.1, iou_loss: 2.2, l1_loss: 1.6, conf_loss: 4.2, cls_loss: 1.2, lr: 2.500e-03, size: 416, ETA: 13:56:18
  850. 2024-02-18 22:33:18 | INFO     | yolox.core.trainer:257 - epoch: 6/300, iter: 80/250, mem: 3871Mb, iter_time: 0.520s, data_time: 0.117s, total_loss: 8.3, iou_loss: 2.3, l1_loss: 1.5, conf_loss: 3.4, cls_loss: 1.2, lr: 2.500e-03, size: 256, ETA: 13:54:42
  851. 2024-02-18 22:33:25 | INFO     | yolox.core.trainer:257 - epoch: 6/300, iter: 90/250, mem: 3871Mb, iter_time: 0.690s, data_time: 0.213s, total_loss: 9.1, iou_loss: 2.3, l1_loss: 1.6, conf_loss: 4.1, cls_loss: 1.1, lr: 2.500e-03, size: 288, ETA: 13:54:41
  852. 2024-02-18 22:33:30 | INFO     | yolox.core.trainer:257 - epoch: 6/300, iter: 100/250, mem: 3871Mb, iter_time: 0.458s, data_time: 0.173s, total_loss: 8.2, iou_loss: 2.6, l1_loss: 1.6, conf_loss: 3.0, cls_loss: 1.0, lr: 2.500e-03, size: 128, ETA: 13:52:33
  853. 2024-02-18 22:33:38 | INFO     | yolox.core.trainer:257 - epoch: 6/300, iter: 110/250, mem: 3871Mb, iter_time: 0.818s, data_time: 0.352s, total_loss: 8.7, iou_loss: 2.3, l1_loss: 1.5, conf_loss: 3.8, cls_loss: 1.1, lr: 2.500e-03, size: 288, ETA: 13:53:42
  854. 2024-02-18 22:33:45 | INFO     | yolox.core.trainer:257 - epoch: 6/300, iter: 120/250, mem: 3871Mb, iter_time: 0.668s, data_time: 0.372s, total_loss: 8.1, iou_loss: 2.5, l1_loss: 1.5, conf_loss: 3.1, cls_loss: 1.0, lr: 2.500e-03, size: 128, ETA: 13:53:29
  855. 2024-02-18 22:33:51 | INFO     | yolox.core.trainer:257 - epoch: 6/300, iter: 130/250, mem: 3871Mb, iter_time: 0.656s, data_time: 0.152s, total_loss: 9.3, iou_loss: 2.4, l1_loss: 1.6, conf_loss: 4.1, cls_loss: 1.2, lr: 2.500e-03, size: 320, ETA: 13:53:10
  856. 2024-02-18 22:33:58 | INFO     | yolox.core.trainer:257 - epoch: 6/300, iter: 140/250, mem: 3871Mb, iter_time: 0.673s, data_time: 0.165s, total_loss: 8.3, iou_loss: 2.2, l1_loss: 1.5, conf_loss: 3.5, cls_loss: 1.1, lr: 2.500e-03, size: 320, ETA: 13:53:00
  857. 2024-02-18 22:34:06 | INFO     | yolox.core.trainer:257 - epoch: 6/300, iter: 150/250, mem: 3871Mb, iter_time: 0.802s, data_time: 0.184s, total_loss: 8.5, iou_loss: 2.1, l1_loss: 1.5, conf_loss: 3.8, cls_loss: 1.2, lr: 2.500e-03, size: 384, ETA: 13:53:57
  858. 2024-02-18 22:34:11 | INFO     | yolox.core.trainer:257 - epoch: 6/300, iter: 160/250, mem: 3871Mb, iter_time: 0.551s, data_time: 0.164s, total_loss: 8.6, iou_loss: 2.4, l1_loss: 1.5, conf_loss: 3.6, cls_loss: 1.1, lr: 2.500e-03, size: 256, ETA: 13:52:43
  859. 2024-02-18 22:34:19 | INFO     | yolox.core.trainer:257 - epoch: 6/300, iter: 170/250, mem: 3871Mb, iter_time: 0.740s, data_time: 0.141s, total_loss: 8.0, iou_loss: 2.0, l1_loss: 1.4, conf_loss: 3.5, cls_loss: 1.1, lr: 2.500e-03, size: 384, ETA: 13:53:08
  860. 2024-02-18 22:34:25 | INFO     | yolox.core.trainer:257 - epoch: 6/300, iter: 180/250, mem: 3871Mb, iter_time: 0.574s, data_time: 0.117s, total_loss: 7.7, iou_loss: 2.1, l1_loss: 1.4, conf_loss: 3.2, cls_loss: 1.0, lr: 2.500e-03, size: 288, ETA: 13:52:08
  861. 2024-02-18 22:34:31 | INFO     | yolox.core.trainer:257 - epoch: 6/300, iter: 190/250, mem: 3871Mb, iter_time: 0.636s, data_time: 0.344s, total_loss: 8.5, iou_loss: 2.7, l1_loss: 1.5, conf_loss: 3.2, cls_loss: 1.2, lr: 2.500e-03, size: 128, ETA: 13:51:39
  862. 2024-02-18 22:34:39 | INFO     | yolox.core.trainer:257 - epoch: 6/300, iter: 200/250, mem: 3871Mb, iter_time: 0.808s, data_time: 0.440s, total_loss: 8.3, iou_loss: 2.4, l1_loss: 1.5, conf_loss: 3.3, cls_loss: 1.0, lr: 2.500e-03, size: 224, ETA: 13:52:38
  863. 2024-02-18 22:34:46 | INFO     | yolox.core.trainer:257 - epoch: 6/300, iter: 210/250, mem: 3871Mb, iter_time: 0.660s, data_time: 0.028s, total_loss: 8.6, iou_loss: 2.0, l1_loss: 1.5, conf_loss: 4.0, cls_loss: 1.1, lr: 2.500e-03, size: 384, ETA: 13:52:22
  864. 2024-02-18 22:34:55 | INFO     | yolox.core.trainer:257 - epoch: 6/300, iter: 220/250, mem: 3871Mb, iter_time: 0.886s, data_time: 0.140s, total_loss: 7.8, iou_loss: 2.0, l1_loss: 1.4, conf_loss: 3.4, cls_loss: 1.0, lr: 2.500e-03, size: 416, ETA: 13:53:58
  865. 2024-02-18 22:35:01 | INFO     | yolox.core.trainer:257 - epoch: 6/300, iter: 230/250, mem: 3871Mb, iter_time: 0.624s, data_time: 0.313s, total_loss: 9.3, iou_loss: 3.0, l1_loss: 1.7, conf_loss: 3.6, cls_loss: 1.0, lr: 2.500e-03, size: 96, ETA: 13:53:23
  866. 2024-02-18 22:35:07 | INFO     | yolox.core.trainer:257 - epoch: 6/300, iter: 240/250, mem: 3871Mb, iter_time: 0.617s, data_time: 0.222s, total_loss: 8.3, iou_loss: 2.3, l1_loss: 1.5, conf_loss: 3.4, cls_loss: 1.1, lr: 2.500e-03, size: 256, ETA: 13:52:45
  867. 2024-02-18 22:35:13 | INFO     | yolox.core.trainer:257 - epoch: 6/300, iter: 250/250, mem: 3871Mb, iter_time: 0.559s, data_time: 0.225s, total_loss: 7.9, iou_loss: 2.4, l1_loss: 1.5, conf_loss: 3.0, cls_loss: 1.0, lr: 2.500e-03, size: 192, ETA: 13:51:39
  868. 2024-02-18 22:35:13 | INFO     | yolox.core.trainer:359 - Save weights to ./YOLOX_outputs/yolox_regnet
  869. 2024-02-18 22:35:14 | INFO     | yolox.core.trainer:199 - ---> start train epoch7
  870. 2024-02-18 22:35:19 | INFO     | yolox.core.trainer:257 - epoch: 7/300, iter: 10/250, mem: 3871Mb, iter_time: 0.591s, data_time: 0.184s, total_loss: 7.9, iou_loss: 2.2, l1_loss: 1.4, conf_loss: 3.1, cls_loss: 1.2, lr: 2.500e-03, size: 256, ETA: 13:50:50
  871. 2024-02-18 22:35:26 | INFO     | yolox.core.trainer:257 - epoch: 7/300, iter: 20/250, mem: 3871Mb, iter_time: 0.699s, data_time: 0.358s, total_loss: 8.0, iou_loss: 2.4, l1_loss: 1.5, conf_loss: 3.0, cls_loss: 1.1, lr: 2.500e-03, size: 192, ETA: 13:50:53
  872. 2024-02-18 22:35:35 | INFO     | yolox.core.trainer:257 - epoch: 7/300, iter: 30/250, mem: 3871Mb, iter_time: 0.846s, data_time: 0.124s, total_loss: 8.7, iou_loss: 2.1, l1_loss: 1.6, conf_loss: 3.9, cls_loss: 1.1, lr: 2.500e-03, size: 416, ETA: 13:52:07
  873. 2024-02-18 22:35:40 | INFO     | yolox.core.trainer:257 - epoch: 7/300, iter: 40/250, mem: 3871Mb, iter_time: 0.524s, data_time: 0.172s, total_loss: 7.9, iou_loss: 2.3, l1_loss: 1.4, conf_loss: 3.0, cls_loss: 1.2, lr: 2.500e-03, size: 224, ETA: 13:50:45
  874. 2024-02-18 22:35:48 | INFO     | yolox.core.trainer:257 - epoch: 7/300, iter: 50/250, mem: 3871Mb, iter_time: 0.757s, data_time: 0.138s, total_loss: 8.6, iou_loss: 2.2, l1_loss: 1.6, conf_loss: 3.7, cls_loss: 1.1, lr: 2.500e-03, size: 384, ETA: 13:51:16
  875. 2024-02-18 22:35:54 | INFO     | yolox.core.trainer:257 - epoch: 7/300, iter: 60/250, mem: 3871Mb, iter_time: 0.585s, data_time: 0.291s, total_loss: 7.7, iou_loss: 2.4, l1_loss: 1.4, conf_loss: 2.9, cls_loss: 1.0, lr: 2.500e-03, size: 128, ETA: 13:50:25
  876. 2024-02-18 22:36:00 | INFO     | yolox.core.trainer:257 - epoch: 7/300, iter: 70/250, mem: 3871Mb, iter_time: 0.610s, data_time: 0.291s, total_loss: 8.3, iou_loss: 2.3, l1_loss: 1.4, conf_loss: 3.5, cls_loss: 1.1, lr: 2.500e-03, size: 192, ETA: 13:49:46
  877. 2024-02-18 22:36:04 | INFO     | yolox.core.trainer:257 - epoch: 7/300, iter: 80/250, mem: 3871Mb, iter_time: 0.472s, data_time: 0.197s, total_loss: 7.6, iou_loss: 2.4, l1_loss: 1.4, conf_loss: 2.8, cls_loss: 1.0, lr: 2.500e-03, size: 128, ETA: 13:48:03
  878. 2024-02-18 22:36:12 | INFO     | yolox.core.trainer:257 - epoch: 7/300, iter: 90/250, mem: 3871Mb, iter_time: 0.743s, data_time: 0.408s, total_loss: 7.6, iou_loss: 2.3, l1_loss: 1.4, conf_loss: 2.9, cls_loss: 1.0, lr: 2.500e-03, size: 160, ETA: 13:48:27
  879. 2024-02-18 22:36:19 | INFO     | yolox.core.trainer:257 - epoch: 7/300, iter: 100/250, mem: 3871Mb, iter_time: 0.748s, data_time: 0.402s, total_loss: 8.4, iou_loss: 2.6, l1_loss: 1.5, conf_loss: 3.2, cls_loss: 1.1, lr: 2.500e-03, size: 160, ETA: 13:48:53
  880. 2024-02-18 22:36:26 | INFO     | yolox.core.trainer:257 - epoch: 7/300, iter: 110/250, mem: 3871Mb, iter_time: 0.654s, data_time: 0.296s, total_loss: 7.9, iou_loss: 2.2, l1_loss: 1.4, conf_loss: 3.1, cls_loss: 1.1, lr: 2.500e-03, size: 224, ETA: 13:48:35
  881. 2024-02-18 22:36:33 | INFO     | yolox.core.trainer:257 - epoch: 7/300, iter: 120/250, mem: 3871Mb, iter_time: 0.726s, data_time: 0.216s, total_loss: inf, iou_loss: 2.3, l1_loss: inf, conf_loss: 3.6, cls_loss: 1.1, lr: 2.500e-03, size: 320, ETA: 13:48:51
  882. 2024-02-18 22:36:37 | INFO     | yolox.core.trainer:257 - epoch: 7/300, iter: 130/250, mem: 3871Mb, iter_time: 0.394s, data_time: 0.103s, total_loss: 7.4, iou_loss: 2.3, l1_loss: 1.3, conf_loss: 2.8, cls_loss: 1.0, lr: 2.500e-03, size: 160, ETA: 13:46:36
  883. 2024-02-18 22:36:46 | INFO     | yolox.core.trainer:257 - epoch: 7/300, iter: 140/250, mem: 3871Mb, iter_time: 0.915s, data_time: 0.333s, total_loss: 8.2, iou_loss: 2.2, l1_loss: 1.4, conf_loss: 3.5, cls_loss: 1.1, lr: 2.500e-03, size: 352, ETA: 13:48:16
  884. 2024-02-18 22:36:53 | INFO     | yolox.core.trainer:257 - epoch: 7/300, iter: 150/250, mem: 3871Mb, iter_time: 0.640s, data_time: 0.253s, total_loss: 7.8, iou_loss: 2.2, l1_loss: 1.4, conf_loss: 3.1, cls_loss: 1.1, lr: 2.500e-03, size: 256, ETA: 13:47:53
  885. 2024-02-18 22:36:58 | INFO     | yolox.core.trainer:257 - epoch: 7/300, iter: 160/250, mem: 3871Mb, iter_time: 0.583s, data_time: 0.113s, total_loss: 7.3, iou_loss: 2.1, l1_loss: 1.3, conf_loss: 2.8, cls_loss: 1.1, lr: 2.500e-03, size: 288, ETA: 13:47:04
  886. 2024-02-18 22:37:06 | INFO     | yolox.core.trainer:257 - epoch: 7/300, iter: 170/250, mem: 3871Mb, iter_time: 0.766s, data_time: 0.157s, total_loss: 7.4, iou_loss: 1.9, l1_loss: 1.4, conf_loss: 3.1, cls_loss: 1.0, lr: 2.500e-03, size: 384, ETA: 13:47:37
  887. 2024-02-18 22:37:11 | INFO     | yolox.core.trainer:257 - epoch: 7/300, iter: 180/250, mem: 3871Mb, iter_time: 0.515s, data_time: 0.252s, total_loss: 8.8, iou_loss: 2.8, l1_loss: 1.5, conf_loss: 3.5, cls_loss: 1.0, lr: 2.500e-03, size: 96, ETA: 13:46:19
  888. 2024-02-18 22:37:18 | INFO     | yolox.core.trainer:257 - epoch: 7/300, iter: 190/250, mem: 3871Mb, iter_time: 0.657s, data_time: 0.359s, total_loss: 7.9, iou_loss: 2.6, l1_loss: 1.4, conf_loss: 2.8, cls_loss: 1.1, lr: 2.500e-03, size: 160, ETA: 13:46:04
  889. 2024-02-18 22:37:25 | INFO     | yolox.core.trainer:257 - epoch: 7/300, iter: 200/250, mem: 3871Mb, iter_time: 0.739s, data_time: 0.232s, total_loss: 8.4, iou_loss: 2.2, l1_loss: 1.4, conf_loss: 3.7, cls_loss: 1.1, lr: 2.500e-03, size: 320, ETA: 13:46:24
  890. 2024-02-18 22:37:31 | INFO     | yolox.core.trainer:257 - epoch: 7/300, iter: 210/250, mem: 3871Mb, iter_time: 0.551s, data_time: 0.102s, total_loss: 7.5, iou_loss: 2.1, l1_loss: 1.4, conf_loss: 3.0, cls_loss: 1.1, lr: 2.500e-03, size: 288, ETA: 13:45:24
  891. 2024-02-18 22:37:39 | INFO     | yolox.core.trainer:257 - epoch: 7/300, iter: 220/250, mem: 3871Mb, iter_time: 0.832s, data_time: 0.218s, total_loss: 8.2, iou_loss: 2.1, l1_loss: 1.4, conf_loss: 3.5, cls_loss: 1.1, lr: 2.500e-03, size: 384, ETA: 13:46:24
  892. 2024-02-18 22:37:45 | INFO     | yolox.core.trainer:257 - epoch: 7/300, iter: 230/250, mem: 3871Mb, iter_time: 0.627s, data_time: 0.172s, total_loss: 8.0, iou_loss: 2.2, l1_loss: 1.4, conf_loss: 3.3, cls_loss: 1.1, lr: 2.500e-03, size: 288, ETA: 13:45:56
  893. 2024-02-18 22:37:50 | INFO     | yolox.core.trainer:257 - epoch: 7/300, iter: 240/250, mem: 3871Mb, iter_time: 0.497s, data_time: 0.196s, total_loss: 8.4, iou_loss: 2.8, l1_loss: 1.5, conf_loss: 3.1, cls_loss: 1.1, lr: 2.500e-03, size: 128, ETA: 13:44:34
  894. 2024-02-18 22:37:58 | INFO     | yolox.core.trainer:257 - epoch: 7/300, iter: 250/250, mem: 3871Mb, iter_time: 0.725s, data_time: 0.311s, total_loss: 7.5, iou_loss: 2.1, l1_loss: 1.2, conf_loss: 3.2, cls_loss: 1.0, lr: 2.499e-03, size: 256, ETA: 13:44:48
  895. 2024-02-18 22:37:58 | INFO     | yolox.core.trainer:359 - Save weights to ./YOLOX_outputs/yolox_regnet
  896. 2024-02-18 22:37:59 | INFO     | yolox.core.trainer:199 - ---> start train epoch8
  897. 2024-02-18 22:38:04 | INFO     | yolox.core.trainer:257 - epoch: 8/300, iter: 10/250, mem: 3871Mb, iter_time: 0.563s, data_time: 0.228s, total_loss: 7.7, iou_loss: 2.4, l1_loss: 1.4, conf_loss: 2.9, cls_loss: 1.0, lr: 2.499e-03, size: 192, ETA: 13:43:54
  898. 2024-02-18 22:38:12 | INFO     | yolox.core.trainer:257 - epoch: 8/300, iter: 20/250, mem: 3871Mb, iter_time: 0.814s, data_time: 0.092s, total_loss: 8.4, iou_loss: 2.2, l1_loss: 1.5, conf_loss: 3.7, cls_loss: 1.0, lr: 2.499e-03, size: 416, ETA: 13:44:45
  899. 2024-02-18 22:38:18 | INFO     | yolox.core.trainer:257 - epoch: 8/300, iter: 30/250, mem: 3871Mb, iter_time: 0.568s, data_time: 0.102s, total_loss: 8.2, iou_loss: 2.2, l1_loss: 1.3, conf_loss: 3.5, cls_loss: 1.1, lr: 2.499e-03, size: 288, ETA: 13:43:54
  900. 2024-02-18 22:38:23 | INFO     | yolox.core.trainer:257 - epoch: 8/300, iter: 40/250, mem: 3871Mb, iter_time: 0.476s, data_time: 0.151s, total_loss: 8.7, iou_loss: 2.6, l1_loss: 1.5, conf_loss: 3.4, cls_loss: 1.1, lr: 2.499e-03, size: 192, ETA: 13:42:26
  901. 2024-02-18 22:38:32 | INFO     | yolox.core.trainer:257 - epoch: 8/300, iter: 50/250, mem: 3871Mb, iter_time: 0.875s, data_time: 0.350s, total_loss: 7.5, iou_loss: 2.0, l1_loss: 1.3, conf_loss: 3.0, cls_loss: 1.1, lr: 2.499e-03, size: 320, ETA: 13:43:41
  902. 2024-02-18 22:38:38 | INFO     | yolox.core.trainer:257 - epoch: 8/300, iter: 60/250, mem: 3871Mb, iter_time: 0.653s, data_time: 0.075s, total_loss: 7.3, iou_loss: 2.0, l1_loss: 1.4, conf_loss: 2.9, cls_loss: 1.0, lr: 2.499e-03, size: 352, ETA: 13:43:25
  903. 2024-02-18 22:38:43 | INFO     | yolox.core.trainer:257 - epoch: 8/300, iter: 70/250, mem: 3871Mb, iter_time: 0.486s, data_time: 0.200s, total_loss: 8.7, iou_loss: 2.8, l1_loss: 1.6, conf_loss: 3.3, cls_loss: 1.0, lr: 2.499e-03, size: 128, ETA: 13:42:02
  904. 2024-02-18 22:38:51 | INFO     | yolox.core.trainer:257 - epoch: 8/300, iter: 80/250, mem: 3871Mb, iter_time: 0.829s, data_time: 0.243s, total_loss: 7.7, iou_loss: 2.2, l1_loss: 1.4, conf_loss: 3.2, cls_loss: 1.0, lr: 2.499e-03, size: 352, ETA: 13:42:57
  905. 2024-02-18 22:38:57 | INFO     | yolox.core.trainer:257 - epoch: 8/300, iter: 90/250, mem: 3871Mb, iter_time: 0.572s, data_time: 0.289s, total_loss: 8.3, iou_loss: 2.7, l1_loss: 1.4, conf_loss: 3.1, cls_loss: 1.0, lr: 2.499e-03, size: 96, ETA: 13:42:10
  906. 2024-02-18 22:39:04 | INFO     | yolox.core.trainer:257 - epoch: 8/300, iter: 100/250, mem: 3871Mb, iter_time: 0.701s, data_time: 0.245s, total_loss: 7.7, iou_loss: 2.2, l1_loss: 1.4, conf_loss: 3.0, cls_loss: 1.1, lr: 2.499e-03, size: 288, ETA: 13:42:14
  907. 2024-02-18 22:39:12 | INFO     | yolox.core.trainer:257 - epoch: 8/300, iter: 110/250, mem: 3871Mb, iter_time: 0.756s, data_time: 0.126s, total_loss: 7.3, iou_loss: 2.0, l1_loss: 1.3, conf_loss: 3.1, cls_loss: 0.9, lr: 2.499e-03, size: 384, ETA: 13:42:39
  908. 2024-02-18 22:39:16 | INFO     | yolox.core.trainer:257 - epoch: 8/300, iter: 120/250, mem: 3871Mb, iter_time: 0.390s, data_time: 0.115s, total_loss: 8.2, iou_loss: 2.8, l1_loss: 1.5, conf_loss: 2.9, cls_loss: 1.0, lr: 2.499e-03, size: 96, ETA: 13:40:41
  909. 2024-02-18 22:39:25 | INFO     | yolox.core.trainer:257 - epoch: 8/300, iter: 130/250, mem: 3871Mb, iter_time: 0.915s, data_time: 0.393s, total_loss: 8.1, iou_loss: 2.1, l1_loss: 1.6, conf_loss: 3.3, cls_loss: 1.1, lr: 2.499e-03, size: 320, ETA: 13:42:08
  910. 2024-02-18 22:39:30 | INFO     | yolox.core.trainer:257 - epoch: 8/300, iter: 140/250, mem: 3871Mb, iter_time: 0.553s, data_time: 0.290s, total_loss: 8.9, iou_loss: 3.2, l1_loss: 1.5, conf_loss: 3.1, cls_loss: 1.1, lr: 2.499e-03, size: 96, ETA: 13:41:14
  911. 2024-02-18 22:39:36 | INFO     | yolox.core.trainer:257 - epoch: 8/300, iter: 150/250, mem: 3871Mb, iter_time: 0.620s, data_time: 0.153s, total_loss: 7.9, iou_loss: 2.3, l1_loss: 1.4, conf_loss: 3.2, cls_loss: 1.1, lr: 2.499e-03, size: 288, ETA: 13:40:47
  912. 2024-02-18 22:39:42 | INFO     | yolox.core.trainer:257 - epoch: 8/300, iter: 160/250, mem: 3871Mb, iter_time: 0.574s, data_time: 0.255s, total_loss: 7.4, iou_loss: 2.4, l1_loss: 1.4, conf_loss: 2.8, cls_loss: 1.0, lr: 2.499e-03, size: 192, ETA: 13:40:02
  913. 2024-02-18 22:39:51 | INFO     | yolox.core.trainer:257 - epoch: 8/300, iter: 170/250, mem: 3871Mb, iter_time: 0.917s, data_time: 0.191s, total_loss: 8.1, iou_loss: 2.0, l1_loss: 1.4, conf_loss: 3.7, cls_loss: 1.0, lr: 2.499e-03, size: 416, ETA: 13:41:28
  914. 2024-02-18 22:39:59 | INFO     | yolox.core.trainer:257 - epoch: 8/300, iter: 180/250, mem: 3871Mb, iter_time: 0.727s, data_time: 0.001s, total_loss: 7.3, iou_loss: 2.1, l1_loss: 1.3, conf_loss: 2.9, cls_loss: 1.0, lr: 2.499e-03, size: 416, ETA: 13:41:41
  915. 2024-02-18 22:40:03 | INFO     | yolox.core.trainer:257 - epoch: 8/300, iter: 190/250, mem: 3871Mb, iter_time: 0.444s, data_time: 0.160s, total_loss: 8.2, iou_loss: 2.6, l1_loss: 1.4, conf_loss: 3.0, cls_loss: 1.1, lr: 2.499e-03, size: 128, ETA: 13:40:07
  916. 2024-02-18 22:40:10 | INFO     | yolox.core.trainer:257 - epoch: 8/300, iter: 200/250, mem: 3871Mb, iter_time: 0.645s, data_time: 0.082s, total_loss: 8.2, iou_loss: 2.2, l1_loss: 1.5, conf_loss: 3.4, cls_loss: 1.1, lr: 2.499e-03, size: 352, ETA: 13:39:50
  917. 2024-02-18 22:40:16 | INFO     | yolox.core.trainer:257 - epoch: 8/300, iter: 210/250, mem: 3871Mb, iter_time: 0.677s, data_time: 0.316s, total_loss: 8.3, iou_loss: 2.3, l1_loss: 1.5, conf_loss: 3.4, cls_loss: 1.2, lr: 2.499e-03, size: 224, ETA: 13:39:45
  918. 2024-02-18 22:40:24 | INFO     | yolox.core.trainer:257 - epoch: 8/300, iter: 220/250, mem: 3871Mb, iter_time: 0.744s, data_time: 0.237s, total_loss: 7.2, iou_loss: 2.0, l1_loss: 1.3, conf_loss: 2.9, cls_loss: 1.1, lr: 2.499e-03, size: 320, ETA: 13:40:04
  919. 2024-02-18 22:40:30 | INFO     | yolox.core.trainer:257 - epoch: 8/300, iter: 230/250, mem: 3871Mb, iter_time: 0.590s, data_time: 0.030s, total_loss: 7.4, iou_loss: 1.9, l1_loss: 1.4, conf_loss: 3.0, cls_loss: 1.1, lr: 2.499e-03, size: 352, ETA: 13:39:27
  920. 2024-02-18 22:40:35 | INFO     | yolox.core.trainer:257 - epoch: 8/300, iter: 240/250, mem: 3871Mb, iter_time: 0.557s, data_time: 0.262s, total_loss: 8.1, iou_loss: 2.5, l1_loss: 1.3, conf_loss: 3.2, cls_loss: 1.0, lr: 2.499e-03, size: 160, ETA: 13:38:37
  921. 2024-02-18 22:40:43 | INFO     | yolox.core.trainer:257 - epoch: 8/300, iter: 250/250, mem: 3871Mb, iter_time: 0.738s, data_time: 0.403s, total_loss: 6.9, iou_loss: 2.2, l1_loss: 1.2, conf_loss: 2.5, cls_loss: 1.0, lr: 2.499e-03, size: 160, ETA: 13:38:54
  922. 2024-02-18 22:40:43 | INFO     | yolox.core.trainer:359 - Save weights to ./YOLOX_outputs/yolox_regnet
  923. 2024-02-18 22:40:44 | INFO     | yolox.core.trainer:199 - ---> start train epoch9
  924. 2024-02-18 22:40:49 | INFO     | yolox.core.trainer:257 - epoch: 9/300, iter: 10/250, mem: 3871Mb, iter_time: 0.486s, data_time: 0.201s, total_loss: 7.7, iou_loss: 2.7, l1_loss: 1.4, conf_loss: 2.6, cls_loss: 1.0, lr: 2.499e-03, size: 96, ETA: 13:37:40
  925. 2024-02-18 22:40:56 | INFO     | yolox.core.trainer:257 - epoch: 9/300, iter: 20/250, mem: 3871Mb, iter_time: 0.725s, data_time: 0.410s, total_loss: 8.2, iou_loss: 2.7, l1_loss: 1.5, conf_loss: 3.0, cls_loss: 1.1, lr: 2.499e-03, size: 128, ETA: 13:37:52
  926. 2024-02-18 22:41:00 | INFO     | yolox.core.trainer:257 - epoch: 9/300, iter: 30/250, mem: 3871Mb, iter_time: 0.393s, data_time: 0.115s, total_loss: 7.6, iou_loss: 2.6, l1_loss: 1.4, conf_loss: 2.6, cls_loss: 1.0, lr: 2.499e-03, size: 96, ETA: 13:36:05
  927. 2024-02-18 22:41:09 | INFO     | yolox.core.trainer:257 - epoch: 9/300, iter: 40/250, mem: 3871Mb, iter_time: 0.885s, data_time: 0.535s, total_loss: 8.1, iou_loss: 2.6, l1_loss: 1.3, conf_loss: 3.0, cls_loss: 1.2, lr: 2.499e-03, size: 128, ETA: 13:37:15
  928. 2024-02-18 22:41:16 | INFO     | yolox.core.trainer:257 - epoch: 9/300, iter: 50/250, mem: 3871Mb, iter_time: 0.771s, data_time: 0.492s, total_loss: 7.6, iou_loss: 2.7, l1_loss: 1.4, conf_loss: 2.5, cls_loss: 1.1, lr: 2.499e-03, size: 96, ETA: 13:37:43
  929. 2024-02-18 22:41:21 | INFO     | yolox.core.trainer:257 - epoch: 9/300, iter: 60/250, mem: 3871Mb, iter_time: 0.510s, data_time: 0.002s, total_loss: 7.6, iou_loss: 2.0, l1_loss: 1.4, conf_loss: 3.1, cls_loss: 1.1, lr: 2.499e-03, size: 320, ETA: 13:36:39
  930. 2024-02-18 22:41:30 | INFO     | yolox.core.trainer:257 - epoch: 9/300, iter: 70/250, mem: 3871Mb, iter_time: 0.890s, data_time: 0.186s, total_loss: 8.7, iou_loss: 2.2, l1_loss: 1.5, conf_loss: 3.9, cls_loss: 1.2, lr: 2.499e-03, size: 416, ETA: 13:37:49
  931. 2024-02-18 22:41:36 | INFO     | yolox.core.trainer:257 - epoch: 9/300, iter: 80/250, mem: 3871Mb, iter_time: 0.566s, data_time: 0.221s, total_loss: 7.4, iou_loss: 2.1, l1_loss: 1.3, conf_loss: 2.9, cls_loss: 1.1, lr: 2.499e-03, size: 224, ETA: 13:37:05
  932. 2024-02-18 22:41:41 | INFO     | yolox.core.trainer:257 - epoch: 9/300, iter: 90/250, mem: 3871Mb, iter_time: 0.515s, data_time: 0.171s, total_loss: 7.1, iou_loss: 2.1, l1_loss: 1.3, conf_loss: 2.7, cls_loss: 1.0, lr: 2.499e-03, size: 224, ETA: 13:36:03
  933. 2024-02-18 22:41:50 | INFO     | yolox.core.trainer:257 - epoch: 9/300, iter: 100/250, mem: 3871Mb, iter_time: 0.842s, data_time: 0.428s, total_loss: 7.6, iou_loss: 2.1, l1_loss: 1.4, conf_loss: 3.1, cls_loss: 1.0, lr: 2.499e-03, size: 256, ETA: 13:36:56
  934. 2024-02-18 22:41:55 | INFO     | yolox.core.trainer:257 - epoch: 9/300, iter: 110/250, mem: 3871Mb, iter_time: 0.552s, data_time: 0.002s, total_loss: 7.4, iou_loss: 2.0, l1_loss: 1.3, conf_loss: 3.0, cls_loss: 1.1, lr: 2.499e-03, size: 320, ETA: 13:36:07
  935. 2024-02-18 22:42:02 | INFO     | yolox.core.trainer:257 - epoch: 9/300, iter: 120/250, mem: 3871Mb, iter_time: 0.696s, data_time: 0.325s, total_loss: 7.3, iou_loss: 2.3, l1_loss: 1.2, conf_loss: 2.8, cls_loss: 1.0, lr: 2.498e-03, size: 224, ETA: 13:36:09
  936. 2024-02-18 22:42:10 | INFO     | yolox.core.trainer:257 - epoch: 9/300, iter: 130/250, mem: 3871Mb, iter_time: 0.800s, data_time: 0.338s, total_loss: 7.9, iou_loss: 2.2, l1_loss: 1.4, conf_loss: 3.1, cls_loss: 1.2, lr: 2.498e-03, size: 288, ETA: 13:36:46
  937. 2024-02-18 22:42:16 | INFO     | yolox.core.trainer:257 - epoch: 9/300, iter: 140/250, mem: 3871Mb, iter_time: 0.623s, data_time: 0.001s, total_loss: 7.1, iou_loss: 1.9, l1_loss: 1.3, conf_loss: 2.9, cls_loss: 1.0, lr: 2.498e-03, size: 384, ETA: 13:36:23
  938. 2024-02-18 22:42:21 | INFO     | yolox.core.trainer:257 - epoch: 9/300, iter: 150/250, mem: 3871Mb, iter_time: 0.496s, data_time: 0.234s, total_loss: 8.1, iou_loss: 2.7, l1_loss: 1.4, conf_loss: 2.9, cls_loss: 1.1, lr: 2.498e-03, size: 96, ETA: 13:35:16
  939. 2024-02-18 22:42:29 | INFO     | yolox.core.trainer:257 - epoch: 9/300, iter: 160/250, mem: 3871Mb, iter_time: 0.726s, data_time: 0.353s, total_loss: 8.1, iou_loss: 2.3, l1_loss: 1.4, conf_loss: 3.3, cls_loss: 1.1, lr: 2.498e-03, size: 224, ETA: 13:35:28
  940. 2024-02-18 22:42:34 | INFO     | yolox.core.trainer:257 - epoch: 9/300, iter: 170/250, mem: 3871Mb, iter_time: 0.541s, data_time: 0.205s, total_loss: 7.4, iou_loss: 2.2, l1_loss: 1.3, conf_loss: 2.8, cls_loss: 1.1, lr: 2.498e-03, size: 192, ETA: 13:34:37
  941. 2024-02-18 22:42:42 | INFO     | yolox.core.trainer:257 - epoch: 9/300, iter: 180/250, mem: 3871Mb, iter_time: 0.790s, data_time: 0.432s, total_loss: 7.4, iou_loss: 2.2, l1_loss: 1.3, conf_loss: 2.8, cls_loss: 1.1, lr: 2.498e-03, size: 192, ETA: 13:35:10
  942. 2024-02-18 22:42:46 | INFO     | yolox.core.trainer:257 - epoch: 9/300, iter: 190/250, mem: 3871Mb, iter_time: 0.450s, data_time: 0.098s, total_loss: 7.1, iou_loss: 2.1, l1_loss: 1.3, conf_loss: 2.7, cls_loss: 1.0, lr: 2.498e-03, size: 224, ETA: 13:33:50
  943. 2024-02-18 22:42:55 | INFO     | yolox.core.trainer:257 - epoch: 9/300, iter: 200/250, mem: 3871Mb, iter_time: 0.851s, data_time: 0.363s, total_loss: 7.4, iou_loss: 2.1, l1_loss: 1.3, conf_loss: 3.0, cls_loss: 1.1, lr: 2.498e-03, size: 288, ETA: 13:34:43
  944. 2024-02-18 22:43:02 | INFO     | yolox.core.trainer:257 - epoch: 9/300, iter: 210/250, mem: 3871Mb, iter_time: 0.733s, data_time: 0.423s, total_loss: 7.0, iou_loss: 2.4, l1_loss: 1.2, conf_loss: 2.5, cls_loss: 0.9, lr: 2.498e-03, size: 128, ETA: 13:34:56
  945. 2024-02-18 22:43:07 | INFO     | yolox.core.trainer:257 - epoch: 9/300, iter: 220/250, mem: 3871Mb, iter_time: 0.508s, data_time: 0.059s, total_loss: 8.1, iou_loss: 2.2, l1_loss: 1.4, conf_loss: 3.5, cls_loss: 1.1, lr: 2.498e-03, size: 288, ETA: 13:33:56
  946. 2024-02-18 22:43:14 | INFO     | yolox.core.trainer:257 - epoch: 9/300, iter: 230/250, mem: 3871Mb, iter_time: 0.682s, data_time: 0.345s, total_loss: 7.1, iou_loss: 2.2, l1_loss: 1.3, conf_loss: 2.6, cls_loss: 1.0, lr: 2.498e-03, size: 192, ETA: 13:33:53
  947. 2024-02-18 22:43:21 | INFO     | yolox.core.trainer:257 - epoch: 9/300, iter: 240/250, mem: 3871Mb, iter_time: 0.721s, data_time: 0.264s, total_loss: 7.6, iou_loss: 2.1, l1_loss: 1.3, conf_loss: 3.2, cls_loss: 1.0, lr: 2.498e-03, size: 288, ETA: 13:34:03
  948. 2024-02-18 22:43:30 | INFO     | yolox.core.trainer:257 - epoch: 9/300, iter: 250/250, mem: 3871Mb, iter_time: 0.818s, data_time: 0.111s, total_loss: 7.8, iou_loss: 2.0, l1_loss: 1.5, conf_loss: 3.2, cls_loss: 1.1, lr: 2.498e-03, size: 416, ETA: 13:34:43
  949. 2024-02-18 22:43:30 | INFO     | yolox.core.trainer:359 - Save weights to ./YOLOX_outputs/yolox_regnet
  950. 2024-02-18 22:43:31 | INFO     | yolox.core.trainer:199 - ---> start train epoch10
  951. 2024-02-18 22:43:36 | INFO     | yolox.core.trainer:257 - epoch: 10/300, iter: 10/250, mem: 3871Mb, iter_time: 0.502s, data_time: 0.001s, total_loss: 6.8, iou_loss: 1.9, l1_loss: 1.3, conf_loss: 2.7, cls_loss: 0.9, lr: 2.498e-03, size: 320, ETA: 13:33:42
  952. 2024-02-18 22:43:39 | INFO     | yolox.core.trainer:257 - epoch: 10/300, iter: 20/250, mem: 3871Mb, iter_time: 0.358s, data_time: 0.056s, total_loss: 7.6, iou_loss: 2.3, l1_loss: 1.3, conf_loss: 2.9, cls_loss: 1.1, lr: 2.498e-03, size: 160, ETA: 13:31:55
  953. 2024-02-18 22:43:48 | INFO     | yolox.core.trainer:257 - epoch: 10/300, iter: 30/250, mem: 3871Mb, iter_time: 0.900s, data_time: 0.364s, total_loss: 7.2, iou_loss: 2.0, l1_loss: 1.3, conf_loss: 2.9, cls_loss: 1.1, lr: 2.498e-03, size: 320, ETA: 13:33:02
  954. 2024-02-18 22:43:55 | INFO     | yolox.core.trainer:257 - epoch: 10/300, iter: 40/250, mem: 3871Mb, iter_time: 0.668s, data_time: 0.338s, total_loss: 7.7, iou_loss: 2.4, l1_loss: 1.5, conf_loss: 2.8, cls_loss: 1.0, lr: 2.498e-03, size: 192, ETA: 13:32:54
  955. 2024-02-18 22:43:59 | INFO     | yolox.core.trainer:257 - epoch: 10/300, iter: 50/250, mem: 3871Mb, iter_time: 0.426s, data_time: 0.126s, total_loss: 7.9, iou_loss: 2.6, l1_loss: 1.4, conf_loss: 2.8, cls_loss: 1.1, lr: 2.498e-03, size: 128, ETA: 13:31:30
  956. 2024-02-18 22:44:08 | INFO     | yolox.core.trainer:257 - epoch: 10/300, iter: 60/250, mem: 3871Mb, iter_time: 0.886s, data_time: 0.346s, total_loss: 7.1, iou_loss: 2.0, l1_loss: 1.2, conf_loss: 2.8, cls_loss: 1.1, lr: 2.498e-03, size: 320, ETA: 13:32:31
  957. 2024-02-18 22:44:14 | INFO     | yolox.core.trainer:257 - epoch: 10/300, iter: 70/250, mem: 3871Mb, iter_time: 0.617s, data_time: 0.303s, total_loss: 7.0, iou_loss: 2.3, l1_loss: 1.2, conf_loss: 2.5, cls_loss: 1.0, lr: 2.498e-03, size: 160, ETA: 13:32:08
  958. 2024-02-18 22:44:21 | INFO     | yolox.core.trainer:257 - epoch: 10/300, iter: 80/250, mem: 3871Mb, iter_time: 0.692s, data_time: 0.081s, total_loss: 7.6, iou_loss: 2.0, l1_loss: 1.4, conf_loss: 3.1, cls_loss: 1.1, lr: 2.498e-03, size: 384, ETA: 13:32:08
  959. 2024-02-18 22:44:27 | INFO     | yolox.core.trainer:257 - epoch: 10/300, iter: 90/250, mem: 3871Mb, iter_time: 0.577s, data_time: 0.309s, total_loss: 8.4, iou_loss: 2.7, l1_loss: 1.4, conf_loss: 3.2, cls_loss: 1.2, lr: 2.498e-03, size: 96, ETA: 13:31:32
  960. 2024-02-18 22:44:31 | INFO     | yolox.core.trainer:257 - epoch: 10/300, iter: 100/250, mem: 3871Mb, iter_time: 0.440s, data_time: 0.125s, total_loss: 6.9, iou_loss: 2.2, l1_loss: 1.2, conf_loss: 2.5, cls_loss: 1.0, lr: 2.498e-03, size: 192, ETA: 13:30:14
  961. 2024-02-18 22:44:40 | INFO     | yolox.core.trainer:257 - epoch: 10/300, iter: 110/250, mem: 3871Mb, iter_time: 0.867s, data_time: 0.388s, total_loss: 6.8, iou_loss: 2.0, l1_loss: 1.3, conf_loss: 2.6, cls_loss: 1.0, lr: 2.498e-03, size: 288, ETA: 13:31:08
  962. 2024-02-18 22:44:47 | INFO     | yolox.core.trainer:257 - epoch: 10/300, iter: 120/250, mem: 3871Mb, iter_time: 0.713s, data_time: 0.314s, total_loss: 6.9, iou_loss: 2.0, l1_loss: 1.2, conf_loss: 2.8, cls_loss: 0.9, lr: 2.497e-03, size: 256, ETA: 13:31:15
  963. 2024-02-18 22:44:52 | INFO     | yolox.core.trainer:257 - epoch: 10/300, iter: 130/250, mem: 3871Mb, iter_time: 0.519s, data_time: 0.064s, total_loss: 7.6, iou_loss: 2.1, l1_loss: 1.4, conf_loss: 3.1, cls_loss: 1.1, lr: 2.497e-03, size: 288, ETA: 13:30:22
  964. 2024-02-18 22:45:00 | INFO     | yolox.core.trainer:257 - epoch: 10/300, iter: 140/250, mem: 3871Mb, iter_time: 0.784s, data_time: 0.267s, total_loss: 7.3, iou_loss: 1.9, l1_loss: 1.3, conf_loss: 3.0, cls_loss: 1.0, lr: 2.497e-03, size: 320, ETA: 13:30:50
  965. 2024-02-18 22:45:06 | INFO     | yolox.core.trainer:257 - epoch: 10/300, iter: 150/250, mem: 3871Mb, iter_time: 0.629s, data_time: 0.122s, total_loss: 6.8, iou_loss: 2.0, l1_loss: 1.3, conf_loss: 2.6, cls_loss: 1.0, lr: 2.497e-03, size: 320, ETA: 13:30:31
  966. 2024-02-18 22:45:12 | INFO     | yolox.core.trainer:257 - epoch: 10/300, iter: 160/250, mem: 3871Mb, iter_time: 0.587s, data_time: 0.254s, total_loss: 6.7, iou_loss: 2.0, l1_loss: 1.2, conf_loss: 2.5, cls_loss: 0.9, lr: 2.497e-03, size: 224, ETA: 13:29:59
  967. 2024-02-18 22:45:19 | INFO     | yolox.core.trainer:257 - epoch: 10/300, iter: 170/250, mem: 3871Mb, iter_time: 0.678s, data_time: 0.390s, total_loss: 6.9, iou_loss: 2.3, l1_loss: 1.3, conf_loss: 2.3, cls_loss: 1.0, lr: 2.497e-03, size: 160, ETA: 13:29:55
  968. 2024-02-18 22:45:24 | INFO     | yolox.core.trainer:257 - epoch: 10/300, iter: 180/250, mem: 3871Mb, iter_time: 0.475s, data_time: 0.179s, total_loss: 7.0, iou_loss: 2.2, l1_loss: 1.3, conf_loss: 2.5, cls_loss: 1.0, lr: 2.497e-03, size: 192, ETA: 13:28:50
  969. 2024-02-18 22:45:33 | INFO     | yolox.core.trainer:257 - epoch: 10/300, iter: 190/250, mem: 3871Mb, iter_time: 0.935s, data_time: 0.313s, total_loss: 7.6, iou_loss: 2.0, l1_loss: 1.4, conf_loss: 3.1, cls_loss: 1.0, lr: 2.497e-03, size: 384, ETA: 13:30:03
  970. 2024-02-18 22:45:39 | INFO     | yolox.core.trainer:257 - epoch: 10/300, iter: 200/250, mem: 3871Mb, iter_time: 0.626s, data_time: 0.269s, total_loss: 7.3, iou_loss: 2.1, l1_loss: 1.3, conf_loss: 2.8, cls_loss: 1.1, lr: 2.497e-03, size: 224, ETA: 13:29:43
  971. 2024-02-18 22:45:46 | INFO     | yolox.core.trainer:257 - epoch: 10/300, iter: 210/250, mem: 3871Mb, iter_time: 0.661s, data_time: 0.135s, total_loss: 6.8, iou_loss: 2.0, l1_loss: 1.2, conf_loss: 2.7, cls_loss: 1.0, lr: 2.497e-03, size: 320, ETA: 13:29:34
  972. 2024-02-18 22:45:52 | INFO     | yolox.core.trainer:257 - epoch: 10/300, iter: 220/250, mem: 3871Mb, iter_time: 0.592s, data_time: 0.303s, total_loss: 7.2, iou_loss: 2.3, l1_loss: 1.3, conf_loss: 2.6, cls_loss: 1.1, lr: 2.497e-03, size: 160, ETA: 13:29:04
  973. 2024-02-18 22:45:58 | INFO     | yolox.core.trainer:257 - epoch: 10/300, iter: 230/250, mem: 3871Mb, iter_time: 0.621s, data_time: 0.330s, total_loss: 7.8, iou_loss: 2.7, l1_loss: 1.4, conf_loss: 2.6, cls_loss: 1.1, lr: 2.497e-03, size: 96, ETA: 13:28:43
  974. 2024-02-18 22:46:06 | INFO     | yolox.core.trainer:257 - epoch: 10/300, iter: 240/250, mem: 3871Mb, iter_time: 0.755s, data_time: 0.129s, total_loss: 7.9, iou_loss: 2.1, l1_loss: 1.3, conf_loss: 3.4, cls_loss: 1.1, lr: 2.497e-03, size: 384, ETA: 13:29:02
  975. 2024-02-18 22:46:11 | INFO     | yolox.core.trainer:257 - epoch: 10/300, iter: 250/250, mem: 3871Mb, iter_time: 0.571s, data_time: 0.284s, total_loss: 8.0, iou_loss: 2.5, l1_loss: 1.3, conf_loss: 3.1, cls_loss: 1.0, lr: 2.497e-03, size: 128, ETA: 13:28:26
  976. 2024-02-18 22:46:11 | INFO     | yolox.core.trainer:359 - Save weights to ./YOLOX_outputs/yolox_regnet
  977. 100%|##########| 125/125 [00:32<00:00,  3.86it/s]
  978. 2024-02-18 22:46:45 | INFO     | yolox.evaluators.coco_evaluator:235 - Evaluate in main process...
  979. 2024-02-18 22:46:52 | INFO     | yolox.evaluators.coco_evaluator:268 - Loading and preparing results...
  980. 2024-02-18 22:46:54 | INFO     | yolox.evaluators.coco_evaluator:268 - DONE (t=2.22s)
  981. 2024-02-18 22:46:54 | INFO     | pycocotools.coco:366 - creating index...
  982. 2024-02-18 22:46:54 | INFO     | pycocotools.coco:366 - index created!
  983. Running per image evaluation...
  984. Evaluate annotation type *bbox*
  985. COCOeval_opt.evaluate() finished in 1.51 seconds.
  986. Accumulating evaluation results...
  987. COCOeval_opt.accumulate() finished in 0.26 seconds.
  988. 2024-02-18 22:46:56 | INFO     | yolox.core.trainer:349 -
  989. Average forward time: 4.75 ms, Average NMS time: 1.02 ms, Average inference time: 5.77 ms
  990.  Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.040
  991.  Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.101
  992.  Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.019
  993.  Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.035
  994.  Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.045
  995.  Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.041
  996.  Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.041
  997.  Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.084
  998.  Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.107
  999.  Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.080
  1000.  Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.113
  1001.  Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.116
  1002.  
  1003. 2024-02-18 22:46:56 | INFO     | yolox.core.trainer:359 - Save weights to ./YOLOX_outputs/yolox_regnet

声明：本文内容由网友自发贡献，不代表【wpsshop博客】立场，版权归原作者所有，本站不承担相应法律责任。如您发现有侵权的内容，请联系我们。转载请注明出处：https://www.wpsshop.cn/w/从前慢现在也慢/article/detail/129799
推荐阅读