Deeplab v3+中的骨干模型resnet（加入atrous)的源码解析，以及普通resnet整个结构的构建过程

加入带洞卷积的resnet结构的构建，以及普通resnet如何通过模块的组合来堆砌深层卷积网络。

第一段代码为deeplab v3+(pytorch版本）中的基本模型改进版resnet的构建过程，

第二段代码为model的全部结构图示，以文字的方式表示，forward过程并未显示其中

 import math
 import torch.nn as nn
 import torch.utils.model_zoo as model_zoo
 from modeling.sync_batchnorm.batchnorm import SynchronizedBatchNorm2d

 class Bottleneck(nn.Module):
     # 此类为resnet的基本模块，在构建resnet不同层的时候，主要以模块的个数以及参数不同来区分。
     expansion = 4

     def __init__(self, inplanes, planes, stride=1, dilation=1, downsample=None, BatchNorm=None):
         super(Bottleneck, self).__init__()
         self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
         self.bn1 = BatchNorm(planes)
         self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride,
                                dilation=dilation, padding=dilation, bias=False)
         self.bn2 = BatchNorm(planes)
         self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
         self.bn3 = BatchNorm(planes * 4)
         self.relu = nn.ReLU(inplace=True)
         self.downsample = downsample
         self.stride = stride
         self.dilation = dilation

     def forward(self, x):
         # 传播的过程，在这里设置残差的操作；
         residual = x

         out = self.conv1(x)
         out = self.bn1(out)
         out = self.relu(out)

         out = self.conv2(out)
         out = self.bn2(out)
         out = self.relu(out)

         out = self.conv3(out)
         out = self.bn3(out)

         if self.downsample is not None:
             residual = self.downsample(x)

         out += residual
         out = self.relu(out)

         return out

 class ResNet(nn.Module):
     # 加入atrous的resnet结构，获取不同的感受野以及上下文信息。
     def __init__(self, block, layers, output_stride, BatchNorm, pretrained=True):
         # 定义resnet的基本结构，通过前面的几层直接设计加上不同参数的bottleneck模块的组合构成；
         # layers参数，在创建resnet类对象的时候，赋予一个数组，在构建多层网络模块的时候调用。
         # block代表模块结构，在这里指的是bottleneck.
         self.inplanes = 64
         super(ResNet, self).__init__()
         blocks = [1, 2, 4]
         if output_stride == 16:
             strides = [1, 2, 2, 1]
             dilations = [1, 1, 1, 2]
         elif output_stride == 8:
             strides = [1, 2, 1, 1]
             dilations = [1, 1, 2, 4]
         else:
             raise NotImplementedError

         # Modules
         self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
                                 bias=False)
         self.bn1 = BatchNorm(64)
         self.relu = nn.ReLU(inplace=True)
         self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
         # 下面通过调用make_layer函数来构造不同参数的bottleneck模块；
         self.layer1 = self._make_layer(block, 64, layers[0], stride=strides[0], dilation=dilations[0], BatchNorm=BatchNorm)
         self.layer2 = self._make_layer(block, 128, layers[1], stride=strides[1], dilation=dilations[1], BatchNorm=BatchNorm)
         self.layer3 = self._make_layer(block, 256, layers[2], stride=strides[2], dilation=dilations[2], BatchNorm=BatchNorm)
         self.layer4 = self._make_MG_unit(block, 512, blocks=blocks, stride=strides[3], dilation=dilations[3], BatchNorm=BatchNorm)
         # self.layer4 = self._make_layer(block, 512, layers[3], stride=strides[3], dilation=dilations[3], BatchNorm=BatchNorm)
         self._init_weight()

         if pretrained:
             self._load_pretrained_model()

     def _make_layer(self, block, planes, blocks, stride=1, dilation=1, BatchNorm=None):
         # block传入的是bottleneck模块；
         # planes参数是改变卷积层参数的重要变量，在这里分别传入64.128.256.512，
         # 目的是为了给conv2d(in_channels,out_channels,kernel_size,stride,……)传递各种参数，

         # blocks是定义有几个参数相同的bottleneck模块，即在最下面的Layers参数【3.4.23.3】，在总模型结构图中可以清晰的看出。
         # dilation参数是为了设置带洞卷积（atrous），默认为1即普通卷积；
         downsample = None
         if stride != 1 or self.inplanes != planes * block.expansion:
             downsample = nn.Sequential(
                 nn.Conv2d(self.inplanes, planes * block.expansion,
                           kernel_size=1, stride=stride, bias=False),
                 BatchNorm(planes * block.expansion),
             )

         layers = []
         layers.append(block(self.inplanes, planes, stride, dilation, downsample, BatchNorm))
         self.inplanes = planes * block.expansion
         for i in range(1, blocks):
             layers.append(block(self.inplanes, planes, dilation=dilation, BatchNorm=BatchNorm))

         return nn.Sequential(*layers)

     def _make_MG_unit(self, block, planes, blocks, stride=1, dilation=1, BatchNorm=None):
         downsample = None
         if stride != 1 or self.inplanes != planes * block.expansion:
             downsample = nn.Sequential(
                 nn.Conv2d(self.inplanes, planes * block.expansion,
                           kernel_size=1, stride=stride, bias=False),
                 BatchNorm(planes * block.expansion),
             )

         layers = []
         layers.append(block(self.inplanes, planes, stride, dilation=blocks[0]*dilation,
                             downsample=downsample, BatchNorm=BatchNorm))
         self.inplanes = planes * block.expansion
         for i in range(1, len(blocks)):
             layers.append(block(self.inplanes, planes, stride=1,
                                 dilation=blocks[i]*dilation, BatchNorm=BatchNorm))

         return nn.Sequential(*layers)

     def forward(self, input):
         x = self.conv1(input)
         x = self.bn1(x)
         x = self.relu(x)
         x = self.maxpool(x)

         x = self.layer1(x)
         low_level_feat = x
         x = self.layer2(x)
         x = self.layer3(x)
         x = self.layer4(x)
         return x, low_level_feat

     def _init_weight(self):
         for m in self.modules():
             if isinstance(m, nn.Conv2d):
                 n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
                 m.weight.data.normal_(0, math.sqrt(2. / n))
             elif isinstance(m, SynchronizedBatchNorm2d):
                 m.weight.data.fill_(1)
                 m.bias.data.zero_()
             elif isinstance(m, nn.BatchNorm2d):
                 m.weight.data.fill_(1)
                 m.bias.data.zero_()

     def _load_pretrained_model(self):
         # pretrain_dict = model_zoo.load_url('https://download.pytorch.org/models/resnet101-5d3b4d8f.pth')
         pretrain_dict = torch.load('/home/huihua/NewDisk/resnet50-19c8e357.pth')
         # 直接加载下载好模型预训练的参数，不用再次下载
         model_dict = {}
         state_dict = self.state_dict()
         for k, v in pretrain_dict.items():
             if k in state_dict:
                 model_dict[k] = v
         state_dict.update(model_dict)
         self.load_state_dict(state_dict)

 def ResNet101(output_stride, BatchNorm, pretrained=True):
     """Constructs a ResNet-101 model.
     Args:
         pretrained (bool): If True, returns a model pre-trained on ImageNet
     """
     model = ResNet(Bottleneck, [3, 4, 23, 3], output_stride, BatchNorm, pretrained=pretrained)
     # 【3,4,23,3】代表make_layer中的block(bottleneck)的块数。resnet源代码中以此来确定resnet50或者101以及更深的。
     return model

 if __name__ == "__main__":
     import torch
     model = ResNet101(BatchNorm=nn.BatchNorm2d, pretrained=True, output_stride=8)
     print(model) #打印模型结构，方便观察如何构造，以及各个参数的含义。
     input = torch.rand(1, 3, 512, 512)
     output, low_level_feat = model(input)
     print(output.size())
     print(low_level_feat.size())

打印出的model结构如下：

 /home/huihua/anaconda3/bin/python /home/huihua/PycharmProjects/untitled/pytorch-deeplab-xception-master/modeling/backbone/resnet.py
 ResNet(
   (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), bias=False)
   (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
   (relu): ReLU(inplace)
   (maxpool): MaxPool2d(kernel_size=, stride=, padding=, dilation=, ceil_mode=False)
   (layer1): Sequential(
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
       (downsample): Sequential(
         (): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
         (): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       )
     )
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
     )
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
     )
   )
   (layer2): Sequential(
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
       (downsample): Sequential(
         (): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
         (): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       )
     )
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
     )
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
     )
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
     )
   )
   (layer3): Sequential(
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), dilation=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
       (downsample): Sequential(
         (): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
         (): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       )
     )
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), dilation=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
     )
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), dilation=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
     )
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), dilation=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
     )
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), dilation=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
     )
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), dilation=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
     )
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), dilation=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
     )
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), dilation=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
     )
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), dilation=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
     )
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), dilation=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
     )
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), dilation=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
     )
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), dilation=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
     )
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), dilation=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
     )
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), dilation=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
     )
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), dilation=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
     )
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), dilation=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
     )
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), dilation=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
     )
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), dilation=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
     )
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), dilation=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
     )
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), dilation=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
     )
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), dilation=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
     )
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), dilation=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
     )
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), dilation=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
     )
   )
   (layer4): Sequential(
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), dilation=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
       (downsample): Sequential(
         (): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
         (): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       )
     )
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), dilation=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
     )
     (): Bottleneck(
       (conv1): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn1): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv2): Conv2d(, , kernel_size=(, ), stride=(, ), padding=(, ), dilation=(, ), bias=False)
       (bn2): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (conv3): Conv2d(, , kernel_size=(, ), stride=(, ), bias=False)
       (bn3): BatchNorm2d(, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
       (relu): ReLU(inplace)
     )
   )
 )
 torch.Size([, , , ])
 torch.Size([, , , ])

 Process finished with exit code