输出网络结构图,mmdetection

2023-12-13 05:30:23

控制台输入:python tools/train.py /home/yuan3080/桌面/detection_paper_6/mmdetection-master1/mmdetection-master_yanhuo/work_dirs/lad_r50_paa_r101_fpn_coco_1x/lad_r50_a_r101_fpn_coco_1x.py

这个是输出方法里面的,不是原始方法。

如下所示,加一个print(model)就可以
,然后运行:控制台输入

之后,之后输出即可,如下所示:

在这里插入图片描述

LAD(
  (backbone): Res2Net(
    (stem): Sequential(
      (0): Conv2d(3, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
      (1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): ReLU(inplace=True)
      (3): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (4): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (5): ReLU(inplace=True)
      (6): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (7): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (8): ReLU(inplace=True)
    )
    (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
    (layer1): Res2Layer(
      (0): Bottle2neck(
        (conv1): Conv2d(64, 104, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn1): BatchNorm2d(104, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv3): Conv2d(104, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): ReLU(inplace=True)
        (downsample): Sequential(
          (0): AvgPool2d(kernel_size=1, stride=1, padding=0)
          (1): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
        (convs): ModuleList(
          (0): Conv2d(26, 26, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): Conv2d(26, 26, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (2): Conv2d(26, 26, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        )
        (bns): ModuleList(
          (0): BatchNorm2d(26, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): BatchNorm2d(26, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): BatchNorm2d(26, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (1): Bottle2neck(
        (conv1): Conv2d(256, 104, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn1): BatchNorm2d(104, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv3): Conv2d(104, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): ReLU(inplace=True)
        (convs): ModuleList(
          (0): Conv2d(26, 26, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): Conv2d(26, 26, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (2): Conv2d(26, 26, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        )
        (bns): ModuleList(
          (0): BatchNorm2d(26, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): BatchNorm2d(26, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): BatchNorm2d(26, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (2): Bottle2neck(
        (conv1): Conv2d(256, 104, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn1): BatchNorm2d(104, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv3): Conv2d(104, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): ReLU(inplace=True)
        (convs): ModuleList(
          (0): Conv2d(26, 26, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): Conv2d(26, 26, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (2): Conv2d(26, 26, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        )
        (bns): ModuleList(
          (0): BatchNorm2d(26, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): BatchNorm2d(26, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): BatchNorm2d(26, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
    )
    (layer2): Res2Layer(
      (0): Bottle2neck(
        (conv1): Conv2d(256, 208, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn1): BatchNorm2d(208, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv3): Conv2d(208, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): ReLU(inplace=True)
        (downsample): Sequential(
          (0): AvgPool2d(kernel_size=2, stride=2, padding=0)
          (1): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
        (pool): AvgPool2d(kernel_size=3, stride=2, padding=1)
        (convs): ModuleList(
          (0): Conv2d(52, 52, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
          (1): Conv2d(52, 52, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
          (2): Conv2d(52, 52, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
        )
        (bns): ModuleList(
          (0): BatchNorm2d(52, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): BatchNorm2d(52, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): BatchNorm2d(52, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (1): Bottle2neck(
        (conv1): Conv2d(512, 208, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn1): BatchNorm2d(208, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv3): Conv2d(208, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): ReLU(inplace=True)
        (convs): ModuleList(
          (0): Conv2d(52, 52, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): Conv2d(52, 52, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (2): Conv2d(52, 52, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        )
        (bns): ModuleList(
          (0): BatchNorm2d(52, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): BatchNorm2d(52, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): BatchNorm2d(52, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (2): Bottle2neck(
        (conv1): Conv2d(512, 208, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn1): BatchNorm2d(208, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv3): Conv2d(208, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): ReLU(inplace=True)
        (convs): ModuleList(
          (0): Conv2d(52, 52, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): Conv2d(52, 52, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (2): Conv2d(52, 52, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        )
        (bns): ModuleList(
          (0): BatchNorm2d(52, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): BatchNorm2d(52, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): BatchNorm2d(52, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (3): Bottle2neck(
        (conv1): Conv2d(512, 208, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn1): BatchNorm2d(208, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv3): Conv2d(208, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): ReLU(inplace=True)
        (convs): ModuleList(
          (0): Conv2d(52, 52, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): Conv2d(52, 52, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (2): Conv2d(52, 52, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        )
        (bns): ModuleList(
          (0): BatchNorm2d(52, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): BatchNorm2d(52, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): BatchNorm2d(52, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
    )
    (layer3): Res2Layer(
      (0): Bottle2neck(
        (conv1): Conv2d(512, 416, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn1): BatchNorm2d(416, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv3): Conv2d(416, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): ReLU(inplace=True)
        (downsample): Sequential(
          (0): AvgPool2d(kernel_size=2, stride=2, padding=0)
          (1): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (2): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
        (pool): AvgPool2d(kernel_size=3, stride=2, padding=1)
        (convs): ModuleList(
          (0): Conv2d(104, 104, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
          (1): Conv2d(104, 104, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
          (2): Conv2d(104, 104, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
        )
        (bns): ModuleList(
          (0): BatchNorm2d(104, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): BatchNorm2d(104, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): BatchNorm2d(104, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (1): Bottle2neck(
        (conv1): Conv2d(1024, 416, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn1): BatchNorm2d(416, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv3): Conv2d(416, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): ReLU(inplace=True)
        (convs): ModuleList(
          (0): Conv2d(104, 104, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): Conv2d(104, 104, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (2): Conv2d(104, 104, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        )
        (bns): ModuleList(
          (0): BatchNorm2d(104, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): BatchNorm2d(104, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): BatchNorm2d(104, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (2): Bottle2neck(
        (conv1): Conv2d(1024, 416, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn1): BatchNorm2d(416, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv3): Conv2d(416, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): ReLU(inplace=True)
        (convs): ModuleList(
          (0): Conv2d(104, 104, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): Conv2d(104, 104, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (2): Conv2d(104, 104, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        )
        (bns): ModuleList(
          (0): BatchNorm2d(104, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): BatchNorm2d(104, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): BatchNorm2d(104, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (3): Bottle2neck(
        (conv1): Conv2d(1024, 416, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn1): BatchNorm2d(416, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv3): Conv2d(416, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): ReLU(inplace=True)
        (convs): ModuleList(
          (0): Conv2d(104, 104, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): Conv2d(104, 104, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (2): Conv2d(104, 104, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        )
        (bns): ModuleList(
          (0): BatchNorm2d(104, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): BatchNorm2d(104, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): BatchNorm2d(104, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (4): Bottle2neck(
        (conv1): Conv2d(1024, 416, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn1): BatchNorm2d(416, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv3): Conv2d(416, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): ReLU(inplace=True)
        (convs): ModuleList(
          (0): Conv2d(104, 104, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): Conv2d(104, 104, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (2): Conv2d(104, 104, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        )
        (bns): ModuleList(
          (0): BatchNorm2d(104, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): BatchNorm2d(104, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): BatchNorm2d(104, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (5): Bottle2neck(
        (conv1): Conv2d(1024, 416, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn1): BatchNorm2d(416, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv3): Conv2d(416, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): ReLU(inplace=True)
        (convs): ModuleList(
          (0): Conv2d(104, 104, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): Conv2d(104, 104, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (2): Conv2d(104, 104, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        )
        (bns): ModuleList(
          (0): BatchNorm2d(104, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): BatchNorm2d(104, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): BatchNorm2d(104, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
    )
    (layer4): Res2Layer(
      (0): Bottle2neck(
        (conv1): Conv2d(1024, 832, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn1): BatchNorm2d(832, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv3): Conv2d(832, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): ReLU(inplace=True)
        (downsample): Sequential(
          (0): AvgPool2d(kernel_size=2, stride=2, padding=0)
          (1): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (2): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
        (pool): AvgPool2d(kernel_size=3, stride=2, padding=1)
        (convs): ModuleList(
          (0): Conv2d(208, 208, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
          (1): Conv2d(208, 208, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
          (2): Conv2d(208, 208, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
        )
        (bns): ModuleList(
          (0): BatchNorm2d(208, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): BatchNorm2d(208, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): BatchNorm2d(208, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (1): Bottle2neck(
        (conv1): Conv2d(2048, 832, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn1): BatchNorm2d(832, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv3): Conv2d(832, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): ReLU(inplace=True)
        (convs): ModuleList(
          (0): Conv2d(208, 208, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): Conv2d(208, 208, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (2): Conv2d(208, 208, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        )
        (bns): ModuleList(
          (0): BatchNorm2d(208, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): BatchNorm2d(208, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): BatchNorm2d(208, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (2): Bottle2neck(
        (conv1): Conv2d(2048, 832, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn1): BatchNorm2d(832, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (conv3): Conv2d(832, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (relu): ReLU(inplace=True)
        (convs): ModuleList(
          (0): Conv2d(208, 208, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): Conv2d(208, 208, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (2): Conv2d(208, 208, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        )
        (bns): ModuleList(
          (0): BatchNorm2d(208, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): BatchNorm2d(208, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): BatchNorm2d(208, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
    )
  )
  init_cfg={'type': 'Pretrained', 'checkpoint': 'torchvision://resnet50'}
  (neck): FPN(
    (lateral_convs): ModuleList(
      (0): ConvModule(
        (conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))
      )
      (1): ConvModule(
        (conv): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1))
      )
      (2): ConvModule(
        (conv): Conv2d(2048, 256, kernel_size=(1, 1), stride=(1, 1))
      )
    )
    (fpn_convs): ModuleList(
      (0): ConvModule(
        (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      )
      (1): ConvModule(
        (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      )
      (2): ConvModule(
        (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      )
      (3): ConvModule(
        (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
      )
      (4): ConvModule(
        (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
      )
    )
  )
  init_cfg={'type': 'Xavier', 'layer': 'Conv2d', 'distribution': 'uniform'}
  (bbox_head): LADHead(
    (loss_cls): FocalLoss()
    (loss_bbox): GIoULoss()
    (relu): ReLU(inplace=True)
    (cls_convs): ModuleList(
      (0): ConvModule(
        (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (gn): GroupNorm(32, 256, eps=1e-05, affine=True)
        (activate): ReLU(inplace=True)
      )
      (1): ConvModule(
        (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (gn): GroupNorm(32, 256, eps=1e-05, affine=True)
        (activate): ReLU(inplace=True)
      )
      (2): ConvModule(
        (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (gn): GroupNorm(32, 256, eps=1e-05, affine=True)
        (activate): ReLU(inplace=True)
      )
      (3): ConvModule(
        (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (gn): GroupNorm(32, 256, eps=1e-05, affine=True)
        (activate): ReLU(inplace=True)
      )
    )
    (reg_convs): ModuleList(
      (0): ConvModule(
        (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (gn): GroupNorm(32, 256, eps=1e-05, affine=True)
        (activate): ReLU(inplace=True)
      )
      (1): ConvModule(
        (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (gn): GroupNorm(32, 256, eps=1e-05, affine=True)
        (activate): ReLU(inplace=True)
      )
      (2): ConvModule(
        (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (gn): GroupNorm(32, 256, eps=1e-05, affine=True)
        (activate): ReLU(inplace=True)
      )
      (3): ConvModule(
        (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (gn): GroupNorm(32, 256, eps=1e-05, affine=True)
        (activate): ReLU(inplace=True)
      )
    )
    (atss_cls): Conv2d(256, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (atss_reg): Conv2d(256, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (atss_centerness): Conv2d(256, 1, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (scales): ModuleList(
      (0): Scale()
      (1): Scale()
      (2): Scale()
      (3): Scale()
      (4): Scale()
    )
    (loss_centerness): CrossEntropyLoss(avg_non_ignore=False)
  )

文章来源:https://blog.csdn.net/qq_44666320/article/details/134958363
本文来自互联网用户投稿,该文观点仅代表作者本人,不代表本站立场。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。