【查看网络结构信息】以霹雳吧啦WZ导师的resnet中的model.py代码为例，尝试了5种打印方式

1. 参考链接

• B站视频：6.2 使用pytorch搭建ResNet并基于迁移学习训练
• github代码地址：https://github.com/WZMIAOMIAO/deep-learning-for-image-processing/blob/master/pytorch_classification/Test5_resnet/model.py
• 在霹雳导师的model.py代码中只添加了if __name__ == '__main__':及以下的代码

2. resnet网络的model.py内容

import torch.nn as nn
import torch


class BasicBlock(nn.Module):
    expansion = 1

    def __init__(self, in_channel, out_channel, stride=1, downsample=None, **kwargs):
        super(BasicBlock, self).__init__()
        self.conv1 = nn.Conv2d(in_channels=in_channel, out_channels=out_channel,
                               kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(out_channel)
        self.relu = nn.ReLU()
        self.conv2 = nn.Conv2d(in_channels=out_channel, out_channels=out_channel,
                               kernel_size=3, stride=1, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(out_channel)
        self.downsample = downsample

    def forward(self, x):
        identity = x
        if self.downsample is not None:
            identity = self.downsample(x)

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

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

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

        return out


class Bottleneck(nn.Module):
    """
    注意：原论文中，在虚线残差结构的主分支上，第一个1x1卷积层的步距是2，第二个3x3卷积层步距是1。
    但在pytorch官方实现过程中是第一个1x1卷积层的步距是1，第二个3x3卷积层步距是2，
    这么做的好处是能够在top1上提升大概0.5%的准确率。
    可参考Resnet v1.5 https://ngc.nvidia.com/catalog/model-scripts/nvidia:resnet_50_v1_5_for_pytorch
    """
    expansion = 4

    def __init__(self, in_channel, out_channel, stride=1, downsample=None,
                 groups=1, width_per_group=64):
        super(Bottleneck, self).__init__()

        width = int(out_channel * (width_per_group / 64.)) * groups

        self.conv1 = nn.Conv2d(in_channels=in_channel, out_channels=width,
                               kernel_size=1, stride=1, bias=False)  # squeeze channels
        self.bn1 = nn.BatchNorm2d(width)
        # -----------------------------------------
        self.conv2 = nn.Conv2d(in_channels=width, out_channels=width, groups=groups,
                               kernel_size=3, stride=stride, bias=False, padding=1)
        self.bn2 = nn.BatchNorm2d(width)
        # -----------------------------------------
        self.conv3 = nn.Conv2d(in_channels=width, out_channels=out_channel*self.expansion,
                               kernel_size=1, stride=1, bias=False)  # unsqueeze channels
        self.bn3 = nn.BatchNorm2d(out_channel*self.expansion)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample

    def forward(self, x):
        identity = x
        if self.downsample is not None:
            identity = self.downsample(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)

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

        return out


class ResNet(nn.Module):

    def __init__(self,
                 block,
                 blocks_num,
                 num_classes=1000,
                 include_top=True,
                 groups=1,
                 width_per_group=64):
        super(ResNet, self).__init__()
        self.include_top = include_top
        self.in_channel = 64

        self.groups = groups
        self.width_per_group = width_per_group

        self.conv1 = nn.Conv2d(3, self.in_channel, kernel_size=7, stride=2,
                               padding=3, bias=False)
        self.bn1 = nn.BatchNorm2d(self.in_channel)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        self.layer1 = self._make_layer(block, 64, blocks_num[0])
        self.layer2 = self._make_layer(block, 128, blocks_num[1], stride=2)
        self.layer3 = self._make_layer(block, 256, blocks_num[2], stride=2)
        self.layer4 = self._make_layer(block, 512, blocks_num[3], stride=2)
        if self.include_top:
            self.avgpool = nn.AdaptiveAvgPool2d((1, 1))  # output size = (1, 1)
            self.fc = nn.Linear(512 * block.expansion, num_classes)

        for m in self.modules():    # lwd edit 应该是在做初始化
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')

    def _make_layer(self, block, channel, block_num, stride=1):
        downsample = None
        if stride != 1 or self.in_channel != channel * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(self.in_channel, channel * block.expansion, kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(channel * block.expansion))

        layers = []
        layers.append(block(self.in_channel,
                            channel,
                            downsample=downsample,
                            stride=stride,
                            groups=self.groups,
                            width_per_group=self.width_per_group))
        self.in_channel = channel * block.expansion

        for _ in range(1, block_num):
            layers.append(block(self.in_channel,
                                channel,
                                groups=self.groups,
                                width_per_group=self.width_per_group))

        return nn.Sequential(*layers)

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

        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)

        if self.include_top:
            x = self.avgpool(x)
            x = torch.flatten(x, 1)
            x = self.fc(x)

        return x


def resnet34(num_classes=1000, include_top=True):
    # https://download.pytorch.org/models/resnet34-333f7ec4.pth
    return ResNet(BasicBlock, [3, 4, 6, 3], num_classes=num_classes, include_top=include_top)


def resnet50(num_classes=1000, include_top=True):
    # https://download.pytorch.org/models/resnet50-19c8e357.pth
    return ResNet(Bottleneck, [3, 4, 6, 3], num_classes=num_classes, include_top=include_top)


def resnet101(num_classes=1000, include_top=True):
    # https://download.pytorch.org/models/resnet101-5d3b4d8f.pth
    return ResNet(Bottleneck, [3, 4, 23, 3], num_classes=num_classes, include_top=include_top)


def resnext50_32x4d(num_classes=1000, include_top=True):
    # https://download.pytorch.org/models/resnext50_32x4d-7cdf4587.pth
    groups = 32
    width_per_group = 4
    return ResNet(Bottleneck, [3, 4, 6, 3],
                  num_classes=num_classes,
                  include_top=include_top,
                  groups=groups,
                  width_per_group=width_per_group)


def resnext101_32x8d(num_classes=1000, include_top=True):
    # https://download.pytorch.org/models/resnext101_32x8d-8ba56ff5.pth
    groups = 32
    width_per_group = 8
    return ResNet(Bottleneck, [3, 4, 23, 3],
                  num_classes=num_classes,
                  include_top=include_top,
                  groups=groups,
                  width_per_group=width_per_group)


if __name__ == '__main__':
    resnet = resnet34()
    print('==================1. 通过print打印网络结构=====================')
    print(resnet)   # 1. 通过print打印网络结构

    # 2. 只能打印出来每层名称和参数量情况（但是有时候又能打印出来输出的特征图大小）
    print('\n================2. torchsummary:只能打印出来每层名称和参数量情况================')
    from torchsummary import summary
    summary(resnet, input_size=(3, 224, 224))

    # 3. 只能用于计算flops和参数量
    print('\n===============3. profile:只能用于计算flops和参数量=====================')
    from thop import profile
    input = torch.randn(1, 3, 224, 224)
    flops, params = profile(resnet, (input,))
    print('flops: %.2f M, params: %.2f M' % (flops / 1e9, params / 1e6))

    # 4. 查看网络参数（只会打印出来含有可训练参数的数量）
    print('\n==============4. named_parameters:查看网络参数（只会打印出来含有可训练参数的数量）=====================')
    for name, parameters in resnet.named_parameters():
        print(name, ':', parameters.size())

    # 5. 每层名字+输出特征图尺寸+参数量
    # 参考链接：https://datawhalechina.github.io/thorough-pytorch/%E7%AC%AC%E4%B8%83%E7%AB%A0/7.1%20%E5%8F%AF%E8%A7%86%E5%8C%96%E7%BD%91%E7%BB%9C%E7%BB%93%E6%9E%84.html
    print('\n===================5. torchinfo:每层名字+输出特征图尺寸+参数量=================')
    from torchinfo import summary
    summary(resnet, (1, 3, 224, 224))  # 1：batch_size 3:图片的通道数 224: 图片的高宽

    # 很奇怪，调用官方库的resnet34网络，就可以直接通过torchsummary打印出来特征层信息
    # import torchvision.models as models
    # from torchsummary import summary
    # resnet34 = models.resnet34() # 实例化模型
    # summary(resnet34, (3, 224, 224))

3. 网络结构打印+展示（resnet34）

3.1 直接使用 print 打印网络结构

	resnet = resnet34()
    print('==================1. 通过print打印网络结构=====================')
    print(resnet)   # 1. 通过print打印网络结构

==================1. 通过print打印网络结构=====================
ResNet(
  (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
  (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (relu): ReLU(inplace=True)
  (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
  (layer1): Sequential(
    (0): BasicBlock(
      (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU()
      (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (1): BasicBlock(
      (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU()
      (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (2): BasicBlock(
      (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU()
      (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
  )
  (layer2): Sequential(
    (0): BasicBlock(
      (conv1): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU()
      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (downsample): Sequential(
        (0): Conv2d(64, 128, kernel_size=(1, 1), stride=(2, 2), bias=False)
        (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (1): BasicBlock(
      (conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU()
      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (2): BasicBlock(
      (conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU()
      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (3): BasicBlock(
      (conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU()
      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
  )
  (layer3): Sequential(
    (0): BasicBlock(
      (conv1): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU()
      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (downsample): Sequential(
        (0): Conv2d(128, 256, kernel_size=(1, 1), stride=(2, 2), bias=False)
        (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (1): BasicBlock(
      (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU()
      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (2): BasicBlock(
      (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU()
      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (3): BasicBlock(
      (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU()
      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (4): BasicBlock(
      (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU()
      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (5): BasicBlock(
      (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU()
      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
  )
  (layer4): Sequential(
    (0): BasicBlock(
      (conv1): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU()
      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (downsample): Sequential(
        (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
        (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (1): BasicBlock(
      (conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU()
      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (2): BasicBlock(
      (conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU()
      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
  )
  (avgpool): AdaptiveAvgPool2d(output_size=(1, 1))
  (fc): Linear(in_features=512, out_features=1000, bias=True)
)

3.2 from torchsummary import summary 打印网络信息

• 没有安装torchsummary的，直接在终端键入pip install torchsummary安装即可
• 只能打印出来每层名称和参数量情况

	# 2. 只能打印出来每层名称和参数量情况（但是有时候又能打印出来输出的特征图大小）
    print('\n================2. torchsummary:只能打印出来每层名称和参数量情况================')
    from torchsummary import summary
    summary(resnet, input_size=(3, 224, 224))

================2. torchsummary:只能打印出来每层名称和参数量情况================
=================================================================
Layer (type:depth-idx)                   Param #
=================================================================
├─Conv2d: 1-1                            9,408
├─BatchNorm2d: 1-2                       128
├─ReLU: 1-3                              --
├─MaxPool2d: 1-4                         --
├─Sequential: 1-5                        --
|    └─BasicBlock: 2-1                   --
|    |    └─Conv2d: 3-1                  36,864
|    |    └─BatchNorm2d: 3-2             128
|    |    └─ReLU: 3-3                    --
|    |    └─Conv2d: 3-4                  36,864
|    |    └─BatchNorm2d: 3-5             128
|    └─BasicBlock: 2-2                   --
|    |    └─Conv2d: 3-6                  36,864
|    |    └─BatchNorm2d: 3-7             128
|    |    └─ReLU: 3-8                    --
|    |    └─Conv2d: 3-9                  36,864
|    |    └─BatchNorm2d: 3-10            128
|    └─BasicBlock: 2-3                   --
|    |    └─Conv2d: 3-11                 36,864
|    |    └─BatchNorm2d: 3-12            128
|    |    └─ReLU: 3-13                   --
|    |    └─Conv2d: 3-14                 36,864
|    |    └─BatchNorm2d: 3-15            128
├─Sequential: 1-6                        --
|    └─BasicBlock: 2-4                   --
|    |    └─Conv2d: 3-16                 73,728
|    |    └─BatchNorm2d: 3-17            256
|    |    └─ReLU: 3-18                   --
|    |    └─Conv2d: 3-19                 147,456
|    |    └─BatchNorm2d: 3-20            256
|    |    └─Sequential: 3-21             8,448
|    └─BasicBlock: 2-5                   --
|    |    └─Conv2d: 3-22                 147,456
|    |    └─BatchNorm2d: 3-23            256
|    |    └─ReLU: 3-24                   --
|    |    └─Conv2d: 3-25                 147,456
|    |    └─BatchNorm2d: 3-26            256
|    └─BasicBlock: 2-6                   --
|    |    └─Conv2d: 3-27                 147,456
|    |    └─BatchNorm2d: 3-28            256
|    |    └─ReLU: 3-29                   --
|    |    └─Conv2d: 3-30                 147,456
|    |    └─BatchNorm2d: 3-31            256
|    └─BasicBlock: 2-7                   --
|    |    └─Conv2d: 3-32                 147,456
|    |    └─BatchNorm2d: 3-33            256
|    |    └─ReLU: 3-34                   --
|    |    └─Conv2d: 3-35                 147,456
|    |    └─BatchNorm2d: 3-36            256
├─Sequential: 1-7                        --
|    └─BasicBlock: 2-8                   --
|    |    └─Conv2d: 3-37                 294,912
|    |    └─BatchNorm2d: 3-38            512
|    |    └─ReLU: 3-39                   --
|    |    └─Conv2d: 3-40                 589,824
|    |    └─BatchNorm2d: 3-41            512
|    |    └─Sequential: 3-42             33,280
|    └─BasicBlock: 2-9                   --
|    |    └─Conv2d: 3-43                 589,824
|    |    └─BatchNorm2d: 3-44            512
|    |    └─ReLU: 3-45                   --
|    |    └─Conv2d: 3-46                 589,824
|    |    └─BatchNorm2d: 3-47            512
|    └─BasicBlock: 2-10                  --
|    |    └─Conv2d: 3-48                 589,824
|    |    └─BatchNorm2d: 3-49            512
|    |    └─ReLU: 3-50                   --
|    |    └─Conv2d: 3-51                 589,824
|    |    └─BatchNorm2d: 3-52            512
|    └─BasicBlock: 2-11                  --
|    |    └─Conv2d: 3-53                 589,824
|    |    └─BatchNorm2d: 3-54            512
|    |    └─ReLU: 3-55                   --
|    |    └─Conv2d: 3-56                 589,824
|    |    └─BatchNorm2d: 3-57            512
|    └─BasicBlock: 2-12                  --
|    |    └─Conv2d: 3-58                 589,824
|    |    └─BatchNorm2d: 3-59            512
|    |    └─ReLU: 3-60                   --
|    |    └─Conv2d: 3-61                 589,824
|    |    └─BatchNorm2d: 3-62            512
|    └─BasicBlock: 2-13                  --
|    |    └─Conv2d: 3-63                 589,824
|    |    └─BatchNorm2d: 3-64            512
|    |    └─ReLU: 3-65                   --
|    |    └─Conv2d: 3-66                 589,824
|    |    └─BatchNorm2d: 3-67            512
├─Sequential: 1-8                        --
|    └─BasicBlock: 2-14                  --
|    |    └─Conv2d: 3-68                 1,179,648
|    |    └─BatchNorm2d: 3-69            1,024
|    |    └─ReLU: 3-70                   --
|    |    └─Conv2d: 3-71                 2,359,296
|    |    └─BatchNorm2d: 3-72            1,024
|    |    └─Sequential: 3-73             132,096
|    └─BasicBlock: 2-15                  --
|    |    └─Conv2d: 3-74                 2,359,296
|    |    └─BatchNorm2d: 3-75            1,024
|    |    └─ReLU: 3-76                   --
|    |    └─Conv2d: 3-77                 2,359,296
|    |    └─BatchNorm2d: 3-78            1,024
|    └─BasicBlock: 2-16                  --
|    |    └─Conv2d: 3-79                 2,359,296
|    |    └─BatchNorm2d: 3-80            1,024
|    |    └─ReLU: 3-81                   --
|    |    └─Conv2d: 3-82                 2,359,296
|    |    └─BatchNorm2d: 3-83            1,024
├─AdaptiveAvgPool2d: 1-9                 --
├─Linear: 1-10                           513,000
=================================================================
Total params: 21,797,672
Trainable params: 21,797,672
Non-trainable params: 0
=================================================================

3.3 from thop import profile 计算出GLOPs和参数量

• 没有安装torchsummary的，直接在终端键入pip install thop安装即可
• 只能用于计算flops和参数量
• 可附带参考我的这篇博客：【论文】参数量Parameters和每秒浮点运算次数FLOPs的单位是多少？答：Paramenter/M，FLOPs/B

# 3. 只能用于计算flops和参数量
    print('\n===============3. profile:只能用于计算flops和参数量=====================')
    from thop import profile
    input = torch.randn(1, 3, 224, 224)
    flops, params = profile(resnet, (input,))
    print('GFLOPs: %.2f M, params: %.2f M' % (flops / 1e9, params / 1e6))

===============3. profile:只能用于计算flops和参数量=====================
[INFO] Register count_convNd() for <class 'torch.nn.modules.conv.Conv2d'>.
[INFO] Register count_normalization() for <class 'torch.nn.modules.batchnorm.BatchNorm2d'>.
[INFO] Register zero_ops() for <class 'torch.nn.modules.activation.ReLU'>.
[INFO] Register zero_ops() for <class 'torch.nn.modules.pooling.MaxPool2d'>.
[INFO] Register zero_ops() for <class 'torch.nn.modules.container.Sequential'>.
[INFO] Register count_adap_avgpool() for <class 'torch.nn.modules.pooling.AdaptiveAvgPool2d'>.
[INFO] Register count_linear() for <class 'torch.nn.modules.linear.Linear'>.
GFLOPs: 3.68 M, params: 21.80 M

3.4 named_parameters 查看网络参数（只会打印出来含有可训练参数名+尺寸）

    # 4. 查看网络参数（只会打印出来含有可训练参数的数量）
    print('\n==============4. named_parameters:查看网络参数（只会打印出来含有可训练参数的数量）=====================')
    for name, parameters in resnet.named_parameters():
        print(name, ':', parameters.size())

==============4. named_parameters:查看网络参数（只会打印出来含有可训练参数的数量）=====================
conv1.weight : torch.Size([64, 3, 7, 7])
bn1.weight : torch.Size([64])
bn1.bias : torch.Size([64])
layer1.0.conv1.weight : torch.Size([64, 64, 3, 3])
layer1.0.bn1.weight : torch.Size([64])
layer1.0.bn1.bias : torch.Size([64])
layer1.0.conv2.weight : torch.Size([64, 64, 3, 3])
layer1.0.bn2.weight : torch.Size([64])
layer1.0.bn2.bias : torch.Size([64])
layer1.1.conv1.weight : torch.Size([64, 64, 3, 3])
layer1.1.bn1.weight : torch.Size([64])
layer1.1.bn1.bias : torch.Size([64])
layer1.1.conv2.weight : torch.Size([64, 64, 3, 3])
layer1.1.bn2.weight : torch.Size([64])
layer1.1.bn2.bias : torch.Size([64])
layer1.2.conv1.weight : torch.Size([64, 64, 3, 3])
layer1.2.bn1.weight : torch.Size([64])
layer1.2.bn1.bias : torch.Size([64])
layer1.2.conv2.weight : torch.Size([64, 64, 3, 3])
layer1.2.bn2.weight : torch.Size([64])
layer1.2.bn2.bias : torch.Size([64])
layer2.0.conv1.weight : torch.Size([128, 64, 3, 3])
layer2.0.bn1.weight : torch.Size([128])
layer2.0.bn1.bias : torch.Size([128])
layer2.0.conv2.weight : torch.Size([128, 128, 3, 3])
layer2.0.bn2.weight : torch.Size([128])
layer2.0.bn2.bias : torch.Size([128])
layer2.0.downsample.0.weight : torch.Size([128, 64, 1, 1])
layer2.0.downsample.1.weight : torch.Size([128])
layer2.0.downsample.1.bias : torch.Size([128])
layer2.1.conv1.weight : torch.Size([128, 128, 3, 3])
layer2.1.bn1.weight : torch.Size([128])
layer2.1.bn1.bias : torch.Size([128])
layer2.1.conv2.weight : torch.Size([128, 128, 3, 3])
layer2.1.bn2.weight : torch.Size([128])
layer2.1.bn2.bias : torch.Size([128])
layer2.2.conv1.weight : torch.Size([128, 128, 3, 3])
layer2.2.bn1.weight : torch.Size([128])
layer2.2.bn1.bias : torch.Size([128])
layer2.2.conv2.weight : torch.Size([128, 128, 3, 3])
layer2.2.bn2.weight : torch.Size([128])
layer2.2.bn2.bias : torch.Size([128])
layer2.3.conv1.weight : torch.Size([128, 128, 3, 3])
layer2.3.bn1.weight : torch.Size([128])
layer2.3.bn1.bias : torch.Size([128])
layer2.3.conv2.weight : torch.Size([128, 128, 3, 3])
layer2.3.bn2.weight : torch.Size([128])
layer2.3.bn2.bias : torch.Size([128])
layer3.0.conv1.weight : torch.Size([256, 128, 3, 3])
layer3.0.bn1.weight : torch.Size([256])
layer3.0.bn1.bias : torch.Size([256])
layer3.0.conv2.weight : torch.Size([256, 256, 3, 3])
layer3.0.bn2.weight : torch.Size([256])
layer3.0.bn2.bias : torch.Size([256])
layer3.0.downsample.0.weight : torch.Size([256, 128, 1, 1])
layer3.0.downsample.1.weight : torch.Size([256])
layer3.0.downsample.1.bias : torch.Size([256])
layer3.1.conv1.weight : torch.Size([256, 256, 3, 3])
layer3.1.bn1.weight : torch.Size([256])
layer3.1.bn1.bias : torch.Size([256])
layer3.1.conv2.weight : torch.Size([256, 256, 3, 3])
layer3.1.bn2.weight : torch.Size([256])
layer3.1.bn2.bias : torch.Size([256])
layer3.2.conv1.weight : torch.Size([256, 256, 3, 3])
layer3.2.bn1.weight : torch.Size([256])
layer3.2.bn1.bias : torch.Size([256])
layer3.2.conv2.weight : torch.Size([256, 256, 3, 3])
layer3.2.bn2.weight : torch.Size([256])
layer3.2.bn2.bias : torch.Size([256])
layer3.3.conv1.weight : torch.Size([256, 256, 3, 3])
layer3.3.bn1.weight : torch.Size([256])
layer3.3.bn1.bias : torch.Size([256])
layer3.3.conv2.weight : torch.Size([256, 256, 3, 3])
layer3.3.bn2.weight : torch.Size([256])
layer3.3.bn2.bias : torch.Size([256])
layer3.4.conv1.weight : torch.Size([256, 256, 3, 3])
layer3.4.bn1.weight : torch.Size([256])
layer3.4.bn1.bias : torch.Size([256])
layer3.4.conv2.weight : torch.Size([256, 256, 3, 3])
layer3.4.bn2.weight : torch.Size([256])
layer3.4.bn2.bias : torch.Size([256])
layer3.5.conv1.weight : torch.Size([256, 256, 3, 3])
layer3.5.bn1.weight : torch.Size([256])
layer3.5.bn1.bias : torch.Size([256])
layer3.5.conv2.weight : torch.Size([256, 256, 3, 3])
layer3.5.bn2.weight : torch.Size([256])
layer3.5.bn2.bias : torch.Size([256])
layer4.0.conv1.weight : torch.Size([512, 256, 3, 3])
layer4.0.bn1.weight : torch.Size([512])
layer4.0.bn1.bias : torch.Size([512])
layer4.0.conv2.weight : torch.Size([512, 512, 3, 3])
layer4.0.bn2.weight : torch.Size([512])
layer4.0.bn2.bias : torch.Size([512])
layer4.0.downsample.0.weight : torch.Size([512, 256, 1, 1])
layer4.0.downsample.1.weight : torch.Size([512])
layer4.0.downsample.1.bias : torch.Size([512])
layer4.1.conv1.weight : torch.Size([512, 512, 3, 3])
layer4.1.bn1.weight : torch.Size([512])
layer4.1.bn1.bias : torch.Size([512])
layer4.1.conv2.weight : torch.Size([512, 512, 3, 3])
layer4.1.bn2.weight : torch.Size([512])
layer4.1.bn2.bias : torch.Size([512])
layer4.2.conv1.weight : torch.Size([512, 512, 3, 3])
layer4.2.bn1.weight : torch.Size([512])
layer4.2.bn1.bias : torch.Size([512])
layer4.2.conv2.weight : torch.Size([512, 512, 3, 3])
layer4.2.bn2.weight : torch.Size([512])
layer4.2.bn2.bias : torch.Size([512])
fc.weight : torch.Size([1000, 512])
fc.bias : torch.Size([1000])

3.5 from torchinfo import summary 打印网络信息

	# 5. 每层名字+输出特征图尺寸+参数量
    # 参考链接：https://datawhalechina.github.io/thorough-pytorch/%E7%AC%AC%E4%B8%83%E7%AB%A0/7.1%20%E5%8F%AF%E8%A7%86%E5%8C%96%E7%BD%91%E7%BB%9C%E7%BB%93%E6%9E%84.html
    print('\n===================5. torchinfo:每层名字+输出特征图尺寸+参数量=================')
    from torchinfo import summary
    summary(resnet, (1, 3, 224, 224))  # 1：batch_size 3:图片的通道数 224: 图片的高宽

===================5. torchinfo:每层名字+输出特征图尺寸+参数量=================
==========================================================================================
Layer (type:depth-idx)                   Output Shape              Param #
==========================================================================================
ResNet                                   [1, 1000]                 --
├─Conv2d: 1-1                            [1, 64, 112, 112]         9,408
├─BatchNorm2d: 1-2                       [1, 64, 112, 112]         128
├─ReLU: 1-3                              [1, 64, 112, 112]         --
├─MaxPool2d: 1-4                         [1, 64, 56, 56]           --
├─Sequential: 1-5                        [1, 64, 56, 56]           --
│    └─BasicBlock: 2-1                   [1, 64, 56, 56]           --
│    │    └─Conv2d: 3-1                  [1, 64, 56, 56]           36,864
│    │    └─BatchNorm2d: 3-2             [1, 64, 56, 56]           128
│    │    └─ReLU: 3-3                    [1, 64, 56, 56]           --
│    │    └─Conv2d: 3-4                  [1, 64, 56, 56]           36,864
│    │    └─BatchNorm2d: 3-5             [1, 64, 56, 56]           128
│    │    └─ReLU: 3-6                    [1, 64, 56, 56]           --
│    └─BasicBlock: 2-2                   [1, 64, 56, 56]           --
│    │    └─Conv2d: 3-7                  [1, 64, 56, 56]           36,864
│    │    └─BatchNorm2d: 3-8             [1, 64, 56, 56]           128
│    │    └─ReLU: 3-9                    [1, 64, 56, 56]           --
│    │    └─Conv2d: 3-10                 [1, 64, 56, 56]           36,864
│    │    └─BatchNorm2d: 3-11            [1, 64, 56, 56]           128
│    │    └─ReLU: 3-12                   [1, 64, 56, 56]           --
│    └─BasicBlock: 2-3                   [1, 64, 56, 56]           --
│    │    └─Conv2d: 3-13                 [1, 64, 56, 56]           36,864
│    │    └─BatchNorm2d: 3-14            [1, 64, 56, 56]           128
│    │    └─ReLU: 3-15                   [1, 64, 56, 56]           --
│    │    └─Conv2d: 3-16                 [1, 64, 56, 56]           36,864
│    │    └─BatchNorm2d: 3-17            [1, 64, 56, 56]           128
│    │    └─ReLU: 3-18                   [1, 64, 56, 56]           --
├─Sequential: 1-6                        [1, 128, 28, 28]          --
│    └─BasicBlock: 2-4                   [1, 128, 28, 28]          --
│    │    └─Sequential: 3-19             [1, 128, 28, 28]          8,448
│    │    └─Conv2d: 3-20                 [1, 128, 28, 28]          73,728
│    │    └─BatchNorm2d: 3-21            [1, 128, 28, 28]          256
│    │    └─ReLU: 3-22                   [1, 128, 28, 28]          --
│    │    └─Conv2d: 3-23                 [1, 128, 28, 28]          147,456
│    │    └─BatchNorm2d: 3-24            [1, 128, 28, 28]          256
│    │    └─ReLU: 3-25                   [1, 128, 28, 28]          --
│    └─BasicBlock: 2-5                   [1, 128, 28, 28]          --
│    │    └─Conv2d: 3-26                 [1, 128, 28, 28]          147,456
│    │    └─BatchNorm2d: 3-27            [1, 128, 28, 28]          256
│    │    └─ReLU: 3-28                   [1, 128, 28, 28]          --
│    │    └─Conv2d: 3-29                 [1, 128, 28, 28]          147,456
│    │    └─BatchNorm2d: 3-30            [1, 128, 28, 28]          256
│    │    └─ReLU: 3-31                   [1, 128, 28, 28]          --
│    └─BasicBlock: 2-6                   [1, 128, 28, 28]          --
│    │    └─Conv2d: 3-32                 [1, 128, 28, 28]          147,456
│    │    └─BatchNorm2d: 3-33            [1, 128, 28, 28]          256
│    │    └─ReLU: 3-34                   [1, 128, 28, 28]          --
│    │    └─Conv2d: 3-35                 [1, 128, 28, 28]          147,456
│    │    └─BatchNorm2d: 3-36            [1, 128, 28, 28]          256
│    │    └─ReLU: 3-37                   [1, 128, 28, 28]          --
│    └─BasicBlock: 2-7                   [1, 128, 28, 28]          --
│    │    └─Conv2d: 3-38                 [1, 128, 28, 28]          147,456
│    │    └─BatchNorm2d: 3-39            [1, 128, 28, 28]          256
│    │    └─ReLU: 3-40                   [1, 128, 28, 28]          --
│    │    └─Conv2d: 3-41                 [1, 128, 28, 28]          147,456
│    │    └─BatchNorm2d: 3-42            [1, 128, 28, 28]          256
│    │    └─ReLU: 3-43                   [1, 128, 28, 28]          --
├─Sequential: 1-7                        [1, 256, 14, 14]          --
│    └─BasicBlock: 2-8                   [1, 256, 14, 14]          --
│    │    └─Sequential: 3-44             [1, 256, 14, 14]          33,280
│    │    └─Conv2d: 3-45                 [1, 256, 14, 14]          294,912
│    │    └─BatchNorm2d: 3-46            [1, 256, 14, 14]          512
│    │    └─ReLU: 3-47                   [1, 256, 14, 14]          --
│    │    └─Conv2d: 3-48                 [1, 256, 14, 14]          589,824
│    │    └─BatchNorm2d: 3-49            [1, 256, 14, 14]          512
│    │    └─ReLU: 3-50                   [1, 256, 14, 14]          --
│    └─BasicBlock: 2-9                   [1, 256, 14, 14]          --
│    │    └─Conv2d: 3-51                 [1, 256, 14, 14]          589,824
│    │    └─BatchNorm2d: 3-52            [1, 256, 14, 14]          512
│    │    └─ReLU: 3-53                   [1, 256, 14, 14]          --
│    │    └─Conv2d: 3-54                 [1, 256, 14, 14]          589,824
│    │    └─BatchNorm2d: 3-55            [1, 256, 14, 14]          512
│    │    └─ReLU: 3-56                   [1, 256, 14, 14]          --
│    └─BasicBlock: 2-10                  [1, 256, 14, 14]          --
│    │    └─Conv2d: 3-57                 [1, 256, 14, 14]          589,824
│    │    └─BatchNorm2d: 3-58            [1, 256, 14, 14]          512
│    │    └─ReLU: 3-59                   [1, 256, 14, 14]          --
│    │    └─Conv2d: 3-60                 [1, 256, 14, 14]          589,824
│    │    └─BatchNorm2d: 3-61            [1, 256, 14, 14]          512
│    │    └─ReLU: 3-62                   [1, 256, 14, 14]          --
│    └─BasicBlock: 2-11                  [1, 256, 14, 14]          --
│    │    └─Conv2d: 3-63                 [1, 256, 14, 14]          589,824
│    │    └─BatchNorm2d: 3-64            [1, 256, 14, 14]          512
│    │    └─ReLU: 3-65                   [1, 256, 14, 14]          --
│    │    └─Conv2d: 3-66                 [1, 256, 14, 14]          589,824
│    │    └─BatchNorm2d: 3-67            [1, 256, 14, 14]          512
│    │    └─ReLU: 3-68                   [1, 256, 14, 14]          --
│    └─BasicBlock: 2-12                  [1, 256, 14, 14]          --
│    │    └─Conv2d: 3-69                 [1, 256, 14, 14]          589,824
│    │    └─BatchNorm2d: 3-70            [1, 256, 14, 14]          512
│    │    └─ReLU: 3-71                   [1, 256, 14, 14]          --
│    │    └─Conv2d: 3-72                 [1, 256, 14, 14]          589,824
│    │    └─BatchNorm2d: 3-73            [1, 256, 14, 14]          512
│    │    └─ReLU: 3-74                   [1, 256, 14, 14]          --
│    └─BasicBlock: 2-13                  [1, 256, 14, 14]          --
│    │    └─Conv2d: 3-75                 [1, 256, 14, 14]          589,824
│    │    └─BatchNorm2d: 3-76            [1, 256, 14, 14]          512
│    │    └─ReLU: 3-77                   [1, 256, 14, 14]          --
│    │    └─Conv2d: 3-78                 [1, 256, 14, 14]          589,824
│    │    └─BatchNorm2d: 3-79            [1, 256, 14, 14]          512
│    │    └─ReLU: 3-80                   [1, 256, 14, 14]          --
├─Sequential: 1-8                        [1, 512, 7, 7]            --
│    └─BasicBlock: 2-14                  [1, 512, 7, 7]            --
│    │    └─Sequential: 3-81             [1, 512, 7, 7]            132,096
│    │    └─Conv2d: 3-82                 [1, 512, 7, 7]            1,179,648
│    │    └─BatchNorm2d: 3-83            [1, 512, 7, 7]            1,024
│    │    └─ReLU: 3-84                   [1, 512, 7, 7]            --
│    │    └─Conv2d: 3-85                 [1, 512, 7, 7]            2,359,296
│    │    └─BatchNorm2d: 3-86            [1, 512, 7, 7]            1,024
│    │    └─ReLU: 3-87                   [1, 512, 7, 7]            --
│    └─BasicBlock: 2-15                  [1, 512, 7, 7]            --
│    │    └─Conv2d: 3-88                 [1, 512, 7, 7]            2,359,296
│    │    └─BatchNorm2d: 3-89            [1, 512, 7, 7]            1,024
│    │    └─ReLU: 3-90                   [1, 512, 7, 7]            --
│    │    └─Conv2d: 3-91                 [1, 512, 7, 7]            2,359,296
│    │    └─BatchNorm2d: 3-92            [1, 512, 7, 7]            1,024
│    │    └─ReLU: 3-93                   [1, 512, 7, 7]            --
│    └─BasicBlock: 2-16                  [1, 512, 7, 7]            --
│    │    └─Conv2d: 3-94                 [1, 512, 7, 7]            2,359,296
│    │    └─BatchNorm2d: 3-95            [1, 512, 7, 7]            1,024
│    │    └─ReLU: 3-96                   [1, 512, 7, 7]            --
│    │    └─Conv2d: 3-97                 [1, 512, 7, 7]            2,359,296
│    │    └─BatchNorm2d: 3-98            [1, 512, 7, 7]            1,024
│    │    └─ReLU: 3-99                   [1, 512, 7, 7]            --
├─AdaptiveAvgPool2d: 1-9                 [1, 512, 1, 1]            --
├─Linear: 1-10                           [1, 1000]                 513,000
==========================================================================================
Total params: 21,797,672
Trainable params: 21,797,672
Non-trainable params: 0
Total mult-adds (G): 3.66
==========================================================================================
Input size (MB): 0.60
Forward/backward pass size (MB): 59.82
Params size (MB): 87.19
Estimated Total Size (MB): 147.61
==========================================================================================

3.6 暂存：奇怪的现象(调用官方库的resnet34网络，就可以直接通过torchsummary打印出来特征层尺寸大小)

	# 很奇怪，调用官方库的resnet34网络，就可以直接通过torchsummary打印出来特征层信息
    import torchvision.models as models
    from torchsummary import summary
    resnet34 = models.resnet34() # 实例化模型
    summary(resnet34, (3, 224, 224))

==========================================================================================
Layer (type:depth-idx)                   Output Shape              Param #
==========================================================================================
├─Conv2d: 1-1                            [-1, 64, 112, 112]        9,408
├─BatchNorm2d: 1-2                       [-1, 64, 112, 112]        128
├─ReLU: 1-3                              [-1, 64, 112, 112]        --
├─MaxPool2d: 1-4                         [-1, 64, 56, 56]          --
├─Sequential: 1-5                        [-1, 64, 56, 56]          --
|    └─BasicBlock: 2-1                   [-1, 64, 56, 56]          --
|    |    └─Conv2d: 3-1                  [-1, 64, 56, 56]          36,864
|    |    └─BatchNorm2d: 3-2             [-1, 64, 56, 56]          128
|    |    └─ReLU: 3-3                    [-1, 64, 56, 56]          --
|    |    └─Conv2d: 3-4                  [-1, 64, 56, 56]          36,864
|    |    └─BatchNorm2d: 3-5             [-1, 64, 56, 56]          128
|    |    └─ReLU: 3-6                    [-1, 64, 56, 56]          --
|    └─BasicBlock: 2-2                   [-1, 64, 56, 56]          --
|    |    └─Conv2d: 3-7                  [-1, 64, 56, 56]          36,864
|    |    └─BatchNorm2d: 3-8             [-1, 64, 56, 56]          128
|    |    └─ReLU: 3-9                    [-1, 64, 56, 56]          --
|    |    └─Conv2d: 3-10                 [-1, 64, 56, 56]          36,864
|    |    └─BatchNorm2d: 3-11            [-1, 64, 56, 56]          128
|    |    └─ReLU: 3-12                   [-1, 64, 56, 56]          --
|    └─BasicBlock: 2-3                   [-1, 64, 56, 56]          --
|    |    └─Conv2d: 3-13                 [-1, 64, 56, 56]          36,864
|    |    └─BatchNorm2d: 3-14            [-1, 64, 56, 56]          128
|    |    └─ReLU: 3-15                   [-1, 64, 56, 56]          --
|    |    └─Conv2d: 3-16                 [-1, 64, 56, 56]          36,864
|    |    └─BatchNorm2d: 3-17            [-1, 64, 56, 56]          128
|    |    └─ReLU: 3-18                   [-1, 64, 56, 56]          --
├─Sequential: 1-6                        [-1, 128, 28, 28]         --
|    └─BasicBlock: 2-4                   [-1, 128, 28, 28]         --
|    |    └─Conv2d: 3-19                 [-1, 128, 28, 28]         73,728
|    |    └─BatchNorm2d: 3-20            [-1, 128, 28, 28]         256
|    |    └─ReLU: 3-21                   [-1, 128, 28, 28]         --
|    |    └─Conv2d: 3-22                 [-1, 128, 28, 28]         147,456
|    |    └─BatchNorm2d: 3-23            [-1, 128, 28, 28]         256
|    |    └─Sequential: 3-24             [-1, 128, 28, 28]         8,448
|    |    └─ReLU: 3-25                   [-1, 128, 28, 28]         --
|    └─BasicBlock: 2-5                   [-1, 128, 28, 28]         --
|    |    └─Conv2d: 3-26                 [-1, 128, 28, 28]         147,456
|    |    └─BatchNorm2d: 3-27            [-1, 128, 28, 28]         256
|    |    └─ReLU: 3-28                   [-1, 128, 28, 28]         --
|    |    └─Conv2d: 3-29                 [-1, 128, 28, 28]         147,456
|    |    └─BatchNorm2d: 3-30            [-1, 128, 28, 28]         256
|    |    └─ReLU: 3-31                   [-1, 128, 28, 28]         --
|    └─BasicBlock: 2-6                   [-1, 128, 28, 28]         --
|    |    └─Conv2d: 3-32                 [-1, 128, 28, 28]         147,456
|    |    └─BatchNorm2d: 3-33            [-1, 128, 28, 28]         256
|    |    └─ReLU: 3-34                   [-1, 128, 28, 28]         --
|    |    └─Conv2d: 3-35                 [-1, 128, 28, 28]         147,456
|    |    └─BatchNorm2d: 3-36            [-1, 128, 28, 28]         256
|    |    └─ReLU: 3-37                   [-1, 128, 28, 28]         --
|    └─BasicBlock: 2-7                   [-1, 128, 28, 28]         --
|    |    └─Conv2d: 3-38                 [-1, 128, 28, 28]         147,456
|    |    └─BatchNorm2d: 3-39            [-1, 128, 28, 28]         256
|    |    └─ReLU: 3-40                   [-1, 128, 28, 28]         --
|    |    └─Conv2d: 3-41                 [-1, 128, 28, 28]         147,456
|    |    └─BatchNorm2d: 3-42            [-1, 128, 28, 28]         256
|    |    └─ReLU: 3-43                   [-1, 128, 28, 28]         --
├─Sequential: 1-7                        [-1, 256, 14, 14]         --
|    └─BasicBlock: 2-8                   [-1, 256, 14, 14]         --
|    |    └─Conv2d: 3-44                 [-1, 256, 14, 14]         294,912
|    |    └─BatchNorm2d: 3-45            [-1, 256, 14, 14]         512
|    |    └─ReLU: 3-46                   [-1, 256, 14, 14]         --
|    |    └─Conv2d: 3-47                 [-1, 256, 14, 14]         589,824
|    |    └─BatchNorm2d: 3-48            [-1, 256, 14, 14]         512
|    |    └─Sequential: 3-49             [-1, 256, 14, 14]         33,280
|    |    └─ReLU: 3-50                   [-1, 256, 14, 14]         --
|    └─BasicBlock: 2-9                   [-1, 256, 14, 14]         --
|    |    └─Conv2d: 3-51                 [-1, 256, 14, 14]         589,824
|    |    └─BatchNorm2d: 3-52            [-1, 256, 14, 14]         512
|    |    └─ReLU: 3-53                   [-1, 256, 14, 14]         --
|    |    └─Conv2d: 3-54                 [-1, 256, 14, 14]         589,824
|    |    └─BatchNorm2d: 3-55            [-1, 256, 14, 14]         512
|    |    └─ReLU: 3-56                   [-1, 256, 14, 14]         --
|    └─BasicBlock: 2-10                  [-1, 256, 14, 14]         --
|    |    └─Conv2d: 3-57                 [-1, 256, 14, 14]         589,824
|    |    └─BatchNorm2d: 3-58            [-1, 256, 14, 14]         512
|    |    └─ReLU: 3-59                   [-1, 256, 14, 14]         --
|    |    └─Conv2d: 3-60                 [-1, 256, 14, 14]         589,824
|    |    └─BatchNorm2d: 3-61            [-1, 256, 14, 14]         512
|    |    └─ReLU: 3-62                   [-1, 256, 14, 14]         --
|    └─BasicBlock: 2-11                  [-1, 256, 14, 14]         --
|    |    └─Conv2d: 3-63                 [-1, 256, 14, 14]         589,824
|    |    └─BatchNorm2d: 3-64            [-1, 256, 14, 14]         512
|    |    └─ReLU: 3-65                   [-1, 256, 14, 14]         --
|    |    └─Conv2d: 3-66                 [-1, 256, 14, 14]         589,824
|    |    └─BatchNorm2d: 3-67            [-1, 256, 14, 14]         512
|    |    └─ReLU: 3-68                   [-1, 256, 14, 14]         --
|    └─BasicBlock: 2-12                  [-1, 256, 14, 14]         --
|    |    └─Conv2d: 3-69                 [-1, 256, 14, 14]         589,824
|    |    └─BatchNorm2d: 3-70            [-1, 256, 14, 14]         512
|    |    └─ReLU: 3-71                   [-1, 256, 14, 14]         --
|    |    └─Conv2d: 3-72                 [-1, 256, 14, 14]         589,824
|    |    └─BatchNorm2d: 3-73            [-1, 256, 14, 14]         512
|    |    └─ReLU: 3-74                   [-1, 256, 14, 14]         --
|    └─BasicBlock: 2-13                  [-1, 256, 14, 14]         --
|    |    └─Conv2d: 3-75                 [-1, 256, 14, 14]         589,824
|    |    └─BatchNorm2d: 3-76            [-1, 256, 14, 14]         512
|    |    └─ReLU: 3-77                   [-1, 256, 14, 14]         --
|    |    └─Conv2d: 3-78                 [-1, 256, 14, 14]         589,824
|    |    └─BatchNorm2d: 3-79            [-1, 256, 14, 14]         512
|    |    └─ReLU: 3-80                   [-1, 256, 14, 14]         --
├─Sequential: 1-8                        [-1, 512, 7, 7]           --
|    └─BasicBlock: 2-14                  [-1, 512, 7, 7]           --
|    |    └─Conv2d: 3-81                 [-1, 512, 7, 7]           1,179,648
|    |    └─BatchNorm2d: 3-82            [-1, 512, 7, 7]           1,024
|    |    └─ReLU: 3-83                   [-1, 512, 7, 7]           --
|    |    └─Conv2d: 3-84                 [-1, 512, 7, 7]           2,359,296
|    |    └─BatchNorm2d: 3-85            [-1, 512, 7, 7]           1,024
|    |    └─Sequential: 3-86             [-1, 512, 7, 7]           132,096
|    |    └─ReLU: 3-87                   [-1, 512, 7, 7]           --
|    └─BasicBlock: 2-15                  [-1, 512, 7, 7]           --
|    |    └─Conv2d: 3-88                 [-1, 512, 7, 7]           2,359,296
|    |    └─BatchNorm2d: 3-89            [-1, 512, 7, 7]           1,024
|    |    └─ReLU: 3-90                   [-1, 512, 7, 7]           --
|    |    └─Conv2d: 3-91                 [-1, 512, 7, 7]           2,359,296
|    |    └─BatchNorm2d: 3-92            [-1, 512, 7, 7]           1,024
|    |    └─ReLU: 3-93                   [-1, 512, 7, 7]           --
|    └─BasicBlock: 2-16                  [-1, 512, 7, 7]           --
|    |    └─Conv2d: 3-94                 [-1, 512, 7, 7]           2,359,296
|    |    └─BatchNorm2d: 3-95            [-1, 512, 7, 7]           1,024
|    |    └─ReLU: 3-96                   [-1, 512, 7, 7]           --
|    |    └─Conv2d: 3-97                 [-1, 512, 7, 7]           2,359,296
|    |    └─BatchNorm2d: 3-98            [-1, 512, 7, 7]           1,024
|    |    └─ReLU: 3-99                   [-1, 512, 7, 7]           --
├─AdaptiveAvgPool2d: 1-9                 [-1, 512, 1, 1]           --
├─Linear: 1-10                           [-1, 1000]                513,000
==========================================================================================
Total params: 21,797,672
Trainable params: 21,797,672
Non-trainable params: 0
Total mult-adds (G): 3.71
==========================================================================================
Input size (MB): 0.57
Forward/backward pass size (MB): 57.05
Params size (MB): 83.15
Estimated Total Size (MB): 140.77
==========================================================================================