Pytorch深度学习—— 自己设计模型训练MNIST（B站刘二大人P10作业）

作业内容：自己设计卷积核大小，池化层、以及线性层的参数，要求有三个卷积层，三个激活层、三个池化层以及三个线性层，用自己设计的卷积网络训练MNIST数据集。

---

选择下图结构的卷积神经网络来进行训练：

步骤：

1. 选择 3 x 3 的卷积核，输入通道为 1，输出通道为 10：此时图像矩阵经过 3 x 3 的卷积核后会小1圈，也就是2个数位，变成 26 x 26，输出通道为10；
2. 选择 2 x 2 的最大池化层：此时图像大小缩短一半，变成 13 x 13，通道数不变；
3. 再次经过 2 x 2 的卷积核，输入通道为 10，输出通道为 20：此时图像再小1个数位，变成 12 * 12，输出通道为20；
4. 再次经过 2 x 2 的最大池化层：此时图像大小缩短一半，变成 6 x 6，通道数不变；
5. 再次经过 3 x 3 的卷积核，输入通道为 20，输出通道为 30：此时图像再小2个数位，变成 4 * 4，输出通道为30；
6. 再次经过 2 x 2 的最大池化层：此时图像大小缩短一半，变成 2 x 2，通道数不变；
7. 最后将图像整型变换成向量，输入到全连接层中：输入一共有 2 x 2 x 30 = 120 个元素，三层线性结构为（120，60），（60，30），（30，10）。

具体代码如下：

1 准备数据集

batch_size = 64
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])
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=False, batch_size=batch_size)

2 建立模型**

class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = torch.nn.Conv2d(1, 10, kernel_size=3)
        self.conv2 = torch.nn.Conv2d(10, 20, kernel_size=2)
        self.conv3 = torch.nn.Conv2d(20, 30, kernel_size=3)
        self.pooling = torch.nn.MaxPool2d(2)
        self.fc1 = torch.nn.Linear(120, 60)
        self.fc2 = torch.nn.Linear(60, 30)
        self.fc3 = torch.nn.Linear(30, 10)

    def forward(self, x):
        batch_size = x.size(0)
        x = F.relu(self.pooling(self.conv1(x)))
        x = F.relu(self.pooling(self.conv2(x)))
        x = F.relu(self.pooling(self.conv3(x)))
        x = x.view(batch_size, -1)
        x = self.fc1(x)
        x = self.fc2(x)
        x = self.fc3(x)
        return x


model = Net()
device=torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)

3 构造损失函数+优化器

criterion = torch.nn.CrossEntropyLoss()
optimizer=optim.SGD(model.parameters(),lr=0.01,momentum=0.5)

4 训练+测试

def train(epoch):
    running_loss=0.0
    for batch_idx,data in enumerate(train_loader,0):
        inputs,target=data
        inputs,target=inputs.to(device),target.to(device)
        optimizer.zero_grad()
        outputs=model(inputs)
        loss=criterion(outputs,target)
        loss.backward()
        optimizer.step()

        running_loss+=loss.item()
        if batch_idx%300==299:
            print('[%d,%.5d] loss:%.3f' % (epoch + 1, batch_idx + 1, running_loss / 2000))
            running_loss=0.0

def test():
    correct=0
    total=0
    with torch.no_grad():
        for data in test_loader:
            inputs, target=data
            inputs,target=inputs.to(device),target.to(device)
            outputs=model(inputs)
            _,predicted=torch.max(outputs.data,dim=1)
            total+=target.size(0)
            correct+=(predicted==target).sum().item()
    print('Accuracy on test set:%d %% [%d%d]' %(100*correct/total,correct,total))

if __name__=='__main__':
    for epoch in range(10):
        train(epoch)
        test()

5 完整代码+运行结果

import torch
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim

batch_size = 64
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])
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=False, batch_size=batch_size)


class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = torch.nn.Conv2d(1, 10, kernel_size=3)
        self.conv2 = torch.nn.Conv2d(10, 20, kernel_size=2)
        self.conv3 = torch.nn.Conv2d(20, 30, kernel_size=3)
        self.pooling = torch.nn.MaxPool2d(2)
        self.fc1 = torch.nn.Linear(120, 60)
        self.fc2 = torch.nn.Linear(60, 30)
        self.fc3 = torch.nn.Linear(30, 10)

    def forward(self, x):
        batch_size = x.size(0)
        x = F.relu(self.pooling(self.conv1(x)))
        x = F.relu(self.pooling(self.conv2(x)))
        x = F.relu(self.pooling(self.conv3(x)))
        x = x.view(batch_size, -1)
        x = self.fc1(x)
        x = self.fc2(x)
        x = self.fc3(x)
        return x


model = Net()
device=torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)

criterion = torch.nn.CrossEntropyLoss()
optimizer=optim.SGD(model.parameters(),lr=0.01,momentum=0.5)


def train(epoch):
    running_loss=0.0
    for batch_idx,data in enumerate(train_loader,0):
        inputs,target=data
        inputs,target=inputs.to(device),target.to(device)
        optimizer.zero_grad()
        outputs=model(inputs)
        loss=criterion(outputs,target)
        loss.backward()
        optimizer.step()

        running_loss+=loss.item()
        if batch_idx%300==299:
            print('[%d,%.5d] loss:%.3f' % (epoch + 1, batch_idx + 1, running_loss / 2000))
            running_loss=0.0

def test():
    correct=0
    total=0
    with torch.no_grad():
        for data in test_loader:
            inputs, target=data
            inputs,target=inputs.to(device),target.to(device)
            outputs=model(inputs)
            _,predicted=torch.max(outputs.data,dim=1)
            total+=target.size(0)
            correct+=(predicted==target).sum().item()
    print('Accuracy on test set:%d %% [%d%d]' %(100*correct/total,correct,total))

if __name__=='__main__':
    for epoch in range(10):
        train(epoch)
        test()

运行结果如下：