Pytorch使用块的深度神经网络VGG

VGG相较于AlexNet的改进是将若干相同的卷积核串联成一个块，然后将这些块再串联起来构建整个网络。

VGG网络用于MNIST手写数字识别，泛化性能测试acc_g=0.65，相较于MLP、LeNet所有提升

完整训练代码见 >>Github链接

VGG块

需要指定块由几个卷积核组成，输入的第一个卷积的通道和最终输出的卷积通道
从代码可以看出，只有第一个卷积核的输入通道会和其他的不一样，其他的卷积核都是一样的。

def vgg_block(num_convs,in_channels,out_channels):
    layers = []
    for _ in range(num_convs):
        layers.append(nn.Conv2d(in_channels,out_channels,kernel_size=3,padding=1))
        layers.append(nn.ReLU())
        in_channels = out_channels
    layers.append(nn.MaxPool2d(kernel_size=2,stride=2))
    return nn.Sequential(*layers)

VGG网络实现

class VGG(nn.Module):
    def __init__(self,conv_arch) -> None:
        super().__init__()
        conv_blks=[]     
        in_channels=1
        for (num_convs,out_channels) in conv_arch:
            conv_blks.append(vgg_block(num_convs,in_channels,out_channels))
            in_channels = out_channels
        self.sequential = nn.Sequential(*conv_blks,nn.Flatten(),
                             nn.Linear(out_channels*7*7,4096),nn.ReLU(),nn.Dropout(0.5),
                             nn.Linear(4096,4096),nn.ReLU(),nn.Dropout(0.5),
                             nn.Linear(4096,10))
           
    def forward(self,x):
        return self.sequential(x)
        
def vgg_block(num_convs,in_channels,out_channels):
    layers = []
    for _ in range(num_convs):
        layers.append(nn.Conv2d(in_channels,out_channels,kernel_size=3,padding=1))
        layers.append(nn.ReLU())
        in_channels = out_channels
    layers.append(nn.MaxPool2d(kernel_size=2,stride=2))
    return nn.Sequential(*layers)