卷积神经网络（四）---再实现MNIST手写数字识别

class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.layer1 = nn.Sequential(
            nn.Conv2d(1, 16, kernel_size=3),  # b, 16, 26, 26
            nn.BatchNorm2d(16),
            nn.ReLU(inplace=True)
        )
        self.layer2 = nn.Sequential(
            nn.Conv2d(16, 32, kernel_size=3),  # b, 32, 24, 24
            nn.BatchNorm2d(32),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=2, stride=2)  # b, 32, 12, 12
        )
        self.layer3 = nn.Sequential(
            nn.Conv2d(32, 64, kernel_size=3),  # b, 64, 10, 10
            nn.BatchNorm2d(64),
            nn.ReLU(inplace=True)
        )
        self.layer4 = nn.Sequential(
            nn.Conv2d(64, 128, kernel_size=3),  # b, 128, 8, 8
            nn.BatchNorm2d(128),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=2, stride=2)  # b, 128, 4, 4
        )
        self.fc = nn.Sequential(
            nn.Linear(128*4*4, 1024),
            nn.ReLU(inplace=True),
            nn.Linear(1024, 128),
            nn.ReLU(inplace=True),
            nn.Linear(128, 10)
        )

    def forward(self, x):
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)
        x = x.view(x.size(0), -1)
        x = self.fc(x)
        return xclass CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.layer1 = nn.Sequential(
            nn.Conv2d(1, 16, kernel_size=3),  # b, 16, 26, 26
            nn.BatchNorm2d(16),
            nn.ReLU(inplace=True)
        )
        self.layer2 = nn.Sequential(
            nn.Conv2d(16, 32, kernel_size=3),  # b, 32, 24, 24
            nn.BatchNorm2d(32),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=2, stride=2)  # b, 32, 12, 12
        )
        self.layer3 = nn.Sequential(
            nn.Conv2d(32, 64, kernel_size=3),  # b, 64, 10, 10
            nn.BatchNorm2d(64),
            nn.ReLU(inplace=True)
        )
        self.layer4 = nn.Sequential(
            nn.Conv2d(64, 128, kernel_size=3),  # b, 128, 8, 8
            nn.BatchNorm2d(128),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=2, stride=2)  # b, 128, 4, 4
        )
        self.fc = nn.Sequential(
            nn.Linear(128*4*4, 1024),
            nn.ReLU(inplace=True),
            nn.Linear(1024, 128),
            nn.ReLU(inplace=True),
            nn.Linear(128, 10)
        )

    def forward(self, x):
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)
        x = x.view(x.size(0), -1)
        x = self.fc(x)
        return x

         上面这个简单的卷积神经网络是运用之前所学到的知识来建立的，里面有4层卷积，2层最大池化，卷积之后使用批标准化加快收敛速度，使用ReLU激活函数增加非线性，最后使用全连接层输出分类得分。最后再测试一下网络的结果，可以看到测试集准确率已经达到了99.27%，比之前使用的3层全连接神经网络要高。可以看到通过增加网络的深度和复杂化网络的结构提高网络的准确率是可行的，下面我们将从数据方面出发来提高网络的准确率。