【一起深度学习——沐的Resnet】

原理图：

实现：

定义残差块：

class Residual(nn.Module):
    def __init__(self,input_channels,num_channels,use_1x1conv=False,strides=1):
        super().__init__()
        """
        blk = Residual(3,3)
        X = torch.rand(4, 3, 6, 6)  (样本数量，通道，高度，宽度)
        """
        # in_channels = 3, num_channels = 3  H2 = (6 -3 + 2*1)/1 +1 = 6 W2 = 6
        # [4,3,6,6] => [4,3,6,6]
        self.conv1 = nn.Conv2d(input_channels,num_channels,kernel_size=3,padding=1,stride=strides)
        # H2 = (6 -3 + 2*1)/1 +1 = 6 W2 = 6
        # [4,3,6,6] => [4,3,6,6]
        self.conv2 = nn.Conv2d(num_channels,num_channels,kernel_size=3,padding=1)
        #若使用1x1的卷积层
        if use_1x1conv:
            # H2 = (6- 1) / 1 +1 =6   W2 = 6
            # [4,3,6,6] => [4,3,6,6]
            self.conv3 = nn.Conv2d(input_channels,num_channels,kernel_size=1,stride=strides)
        else:
            self.conv3 = None
        self.bn1 = nn.BatchNorm2d(num_channels)
        self.bn2 = nn.BatchNorm2d(num_channels)
        self.relu = nn.ReLU(inplace=True)
    def forward(self,x):
        Y = F.relu(self.bn1(self.conv1(x)))
        Y = self.bn2(self.conv2(Y))
        if self.conv3:
            x = self.conv3(x)
        Y += x
        return F.relu(Y)

其中，该代码实现了两种不同的网络，一种是x直接传送，另一种是x经过卷积后再进行传送。原理图如下：

定义Resnet模型：

b1 = nn.Sequential(nn.Conv2d(1, 64, kernel_size=7, stride=2, padding=3),
                   nn.BatchNorm2d(64), nn.ReLU(),
                   nn.MaxPool2d(kernel_size=3, stride=2, padding=1))

b2 = nn.Sequential(*resnet_block(64, 64, 2, first_block=True))
b3 = nn.Sequential(*resnet_block(64, 128, 2))
b4 = nn.Sequential(*resnet_block(128, 256, 2))
b5 = nn.Sequential(*resnet_block(256, 512, 2))

net = nn.Sequential(b1, b2, b3, b4, b5,
                    nn.AdaptiveAvgPool2d((1,1)),
                    nn.Flatten(), nn.Linear(512, 10))

运行测试：

lr, num_epochs, batch_size = 0.05, 10, 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, resize=96)
d2l.train_ch6(net, train_iter, test_iter, num_epochs, lr, d2l.try_gpu())

输出结果：

loss 0.013, train acc 0.997, test acc 0.917
936.3 examples/sec on cuda:0