卷积网络入门代码备注解释

最近在学习卷积神经网络，根据之前博主的卷积神经网络的代码，做了一些备注，对于代码不太熟悉的可以作为参考。数据集是MNIST。

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

# prepare dataset

batch_size = 64

"""
transforms.ToTensor()----把灰度范围从0-255转换到0-1
transforms.Normalize()---用均值和标准差归一化，归一化张量图像，将0-1转换到（-1，1）
"""
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)


# design model using class


class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = torch.nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = torch.nn.Conv2d(10, 20, kernel_size=5)
        self.pooling = torch.nn.MaxPool2d(2)
        self.fc = torch.nn.Linear(320, 10)

    def forward(self, x):
        # flatten data from (n,1,28,28) to (n, 784)
        batch_size = x.size(0)
        x = F.relu(self.pooling(self.conv1(x)))
        x = F.relu(self.pooling(self.conv2(x)))
        x = x.view(batch_size, -1)  # -1 此处自动算出的是320
        x = self.fc(x)

        return x


model = Net()

# construct loss and optimizer
criterion = torch.nn.CrossEntropyLoss()
# lr---学习旅，momentum---动量因子，optimizer---构建一个优化器
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)


# training cycle forward, backward, update


def train(epoch):
    # running_loss记录在这次epoch中每个batch的损失和
    running_loss = 0.0
    for batch_idx, data in enumerate(train_loader, 0):
        inputs, target = data
        # 梯度初始化为零，把loss关于weight的导数变为0
        optimizer.zero_grad()

        outputs = model(inputs)
        loss = criterion(outputs, target)
        # 反向传播求梯度
        loss.backward()
        # 更新所有参数
        optimizer.step()

        # 为了计算这次epoch的loss平均值
        running_loss += loss.item()
        if batch_idx % 300 == 299:
            print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_idx + 1, running_loss / 300))
            running_loss = 0.0


def test():
    correct = 0
    total = 0
    # 被with torch.no_grad()包围的代码，不用跟踪反向梯度计算
    with torch.no_grad():
        for data in test_loader:
            images, labels = data
            outputs = model(images)
            # 输出最大值所在索引，就是最大的那个数字是第几个，从0开始
            _, predicted = torch.max(outputs.data, dim=1)
            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()