第J1周：ResNet-50算法实战与解析

•  🍨 本文为🔗365天深度学习训练营 中的学习记录博客
• 🍖 原作者：K同学啊 | 接辅导、项目定制
• ResNet模型搭建

• import torch
  import torch.nn as nn
  import torch.nn.functional as F
  
  class IdentityBlock(nn.Module):
      def __init__(self, in_channels, filters, kernel_size):
          super(IdentityBlock, self).__init__()
          f1, f2, f3 = filters
          self.conv1 = nn.Conv2d(in_channels, f1, kernel_size=1)
          self.bn1 = nn.BatchNorm2d(f1)
          self.conv2 = nn.Conv2d(f1, f2, kernel_size=kernel_size, padding='same')
          self.bn2 = nn.BatchNorm2d(f2)
          self.conv3 = nn.Conv2d(f2, f3, kernel_size=1)
          self.bn3 = nn.BatchNorm2d(f3)
          self.relu = nn.ReLU(inplace=True)
  
      def forward(self, x):
          identity = x
          out = self.relu(self.bn1(self.conv1(x)))
          out = self.relu(self.bn2(self.conv2(out)))
          out = self.bn3(self.conv3(out))
          out += identity
          out = self.relu(out)
          return out
  
  class ConvBlock(nn.Module):
      def __init__(self, in_channels, filters, kernel_size, stride=2):
          super(ConvBlock, self).__init__()
          f1, f2, f3 = filters
          self.conv1 = nn.Conv2d(in_channels, f1, kernel_size=1, stride=stride)
          self.bn1 = nn.BatchNorm2d(f1)
          self.conv2 = nn.Conv2d(f1, f2, kernel_size=kernel_size, padding='same')
          self.bn2 = nn.BatchNorm2d(f2)
          self.conv3 = nn.Conv2d(f2, f3, kernel_size=1)
          self.bn3 = nn.BatchNorm2d(f3)
          self.shortcut = nn.Sequential(
              nn.Conv2d(in_channels, f3, kernel_size=1, stride=stride),
              nn.BatchNorm2d(f3)
          )
          self.relu = nn.ReLU(inplace=True)
  
      def forward(self, x):
          identity = self.shortcut(x)
          out = self.relu(self.bn1(self.conv1(x)))
          out = self.relu(self.bn2(self.conv2(out)))
          out = self.bn3(self.conv3(out))
          out += identity
          out = self.relu(out)
          return out
  
  class ResNet50(nn.Module):
      def __init__(self, input_shape, num_classes=1000):
          super(ResNet50, self).__init__()
          self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3)
          self.bn1 = nn.BatchNorm2d(64)
          self.pool1 = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
          self.layer1 = self._make_layer(64, [64, 64, 256], stride=1, num_blocks=3)
          self.layer2 = self._make_layer(256, [128, 128, 512], stride=2, num_blocks=4)
          self.layer3 = self._make_layer(512, [256, 256, 1024], stride=2, num_blocks=6)
          self.layer4 = self._make_layer(1024, [512, 512, 2048], stride=2, num_blocks=3)
          self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
          self.fc = nn.Linear(2048, num_classes)
  
      def _make_layer(self, in_channels, filters, stride, num_blocks):
          layers = [ConvBlock(in_channels, filters, kernel_size=3, stride=stride)]
          for _ in range(1, num_blocks):
              layers.append(IdentityBlock(filters[2], filters, kernel_size=3))
          return nn.Sequential(*layers)
  
      def forward(self, x):
          x = F.relu(self.bn1(self.conv1(x)))
          x = self.pool1(x)
          x = self.layer1(x)
          x = self.layer2(x)
          x = self.layer3(x)
          x = self.layer4(x)
          x = self.avgpool(x)
          x = torch.flatten(x, 1)
          x = self.fc(x)
          return x
  
  device = "cuda" if torch.cuda.is_available() else "cpu"
  print("Using {} device".format(device))
      
  model = ResNet50((224,224,3)).to(device)
  model

  总结：过程有点艰难，TF的代码还是不太熟悉，不过结合图还能自己分析逻辑敲出代码继续加油