Resnet网络详细结构（针对Cifar10）

Resnet网络详细结构（针对Cifar10）

结构

具体结构（Pytorch）

1. conv1

   (conv1): Conv2d(3, 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(inplace=True)
   (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
   

   • Conv2d：

     • Conv2d(in_channels, out_channels, kernel_size, stride=1,padding=0, dilation=1, groups=1,bias=True, padding_mode=‘zeros’)
             (输入通道，输出通道数，F：卷积核的大小，S：步长，P：padding，dilation：卷积核的间隔，空洞卷积)
       

     • 卷积核维度计算公式：

     \[W_o = (W_i-F+2P)/S+1
     \]

   • BatchNorm2d：批归一化（Batch Normalization）的目的是使我们的一批（Batch）的feature map满足均值为0，方差为1的分布规律

     • BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True,track_running_stats=True)
       

   • ReLU：激活函数

   • MaxPool2d：最大池化，下采样

2. layer1

   (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(inplace=True)
           (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(inplace=True)
           (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)))
   

3. layer3：……

4. layer4：……

5. avgpool

   • AdaptiveAvgPool2d ：自适应平均池化

     • torch.nn.AdaptiveAvgPool1d(output_size)
       

     • 对输入进行自适应平均池化，输出指定为output_size，特征维数不变，根据输出大小计算核池化的核大小，步长

6. fc：全连接

(avgpool): AdaptiveAvgPool2d(output_size=(1, 1))
(fc): Linear(in_features=512, out_features=10, bias=True)