卷积神经网络高级篇--ResNet实现mnist手写识别

定义

若将输入设为X，将某一有参网络层设为H，那么以X为输入的此层的输出将为H(X)。一般的CNN网络如Alexnet/VGG等会直接通过训练学习出参数函数H的表达，从而直接学习X -> H(X)。

而残差学习则是致力于使用多个有参网络层来学习输入、输出之间的参差即H(X) - X即学习X -> (H(X) - X) + X。其中X这一部分为直接的identity mapping，而H(X) - X则为有参网络层要学习的输入输出间残差。

ResNet结构及残差块代码实现

代码 

import torch
import torch.nn.functional as F
from torchvision import transforms#是一个常用的图片变换类
from torchvision import datasets
from torch.utils.data import DataLoader
batch_size=64
transform=transforms.Compose(
    [
        transforms.ToTensor(),#把数据转换成张量
        transforms.Normalize((0.1307,),(0.3081,))#0.1307是均值，0.3081是标准差
    ]
)
train_dataset=datasets.MNIST(root='../dataset/mnist',
                             train=True,
                             download=True,
                             transform=transform)
train_loader=DataLoader(train_dataset,
                        shuffle=True,
                        batch_size=batch_size)
test_dataset=datasets.MNIST(root='../dataset/mnist',
                            train=False,
                            download=True,
                            transform=transform)
test_loader=DataLoader(test_dataset,
                       shuffle=True,
                       batch_size=batch_size)
class ResidualBlock(torch.nn.Module):
    def __init__(self,channels):
        super(ResidualBlock, self).__init__()
        self.channels=channels
        self.conv1=torch.nn.Conv2d(channels,channels,kernel_size=3,padding=1)
        self.conv2=torch.nn.Conv2d(channels,channels,kernel_size=3,padding=1)
    def forward(self,x):
        y=F.relu(self.conv1(x))
        y=self.conv2(y)
        return F.relu(x+y)
class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1=torch.nn.Conv2d(1,16,kernel_size=5)
        self.conv2=torch.nn.Conv2d(16,32,kernel_size=5)
        self.mp=torch.nn.MaxPool2d(2)

        self.rblock1=ResidualBlock(16)
        self.rblock2=ResidualBlock(32)

        self.fc=torch.nn.Linear(512,10)
    def forward(self,x):
        in_size=x.size(0)
        x=self.mp(F.relu(self.conv1(x)))
        x=self.rblock1(x)
        x=self.mp(F.relu(self.conv2(x)))
        x=self.rblock2(x)
        x=x.view(in_size,-1)
        x=self.fc(x)
        return x
model=Net()
criterion=torch.nn.CrossEntropyLoss() #使用交叉熵损失
optimizer=torch.optim.SGD(model.parameters(),lr=0.1,momentum=0.5)#momentum表示冲量，冲出局部最小
def train(epochs):
    running_loss=0.0
    for batch_idx,data in enumerate(train_loader,0):
        inputs,target=data
        optimizer.zero_grad()
        #前馈+反馈+更新
        outputs=model(inputs)
        loss=criterion(outputs,target)
        loss.backward()
        optimizer.step()

        running_loss+=loss.item()
        if batch_idx%300==299:#不让他每一次小的迭代就输出，而是300次小迭代再输出一次
            print('[%d,%5d] loss:%.3f'%(epoch+1,batch_idx+1,running_loss/300))
            running_loss=0.0

def test():
    correct=0
    total=0
    with torch.no_grad():#下面的代码就不会再计算梯度
        for data in test_loader:
            images,labels=data
            outputs=model(images)
            _,predicted=torch.max(outputs.data,dim=1)#_为每一行的最大值，predicted表示每一行最大值的下标
            total+=labels.size(0)
            correct+=(predicted==labels).sum().item()
    print('Accuracy on test set:%d %%'%(100*correct/total))
if __name__ == '__main__':
    for epoch in range(10):
        train(epoch)
        test()