CNN

import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms

# Device configuration
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')

# Hyper parameters
num_epochs = 5
num_classes = 10
batch_size = 100
learning_rate = 0.001

# MNIST dataset
train_dataset = torchvision.datasets.MNIST(root='../data/',train=True, transform=transforms.ToTensor(), download=True)

test_dataset = torchvision.datasets.MNIST(root='../data/',train=False, transform=transforms.ToTensor())


# Data loader
train_loader = torch.utils.data.DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=True)

test_loader = torch.utils.data.DataLoader(dataset=test_dataset, batch_size=batch_size, shuffle=False)


# Convolutional neural network (two convolutional layers)
class ConvNet(nn.Module):
    def __init__(self, num_classes=10):
        super(ConvNet, self).__init__()
        self.layer1 = nn.Sequential(
            nn.Conv2d(1, 16, kernel_size=5, stride=1, padding=2),# nn.Conv2d的功能是：对由多个输入平面组成的输入信号进行二维卷积，输入信号的形式为(N,Cin,H,W) ；N表示batch size，Cin 表示channel个数，H，W分别表示特征图的高和宽。
            nn.BatchNorm2d(16),   # 对小批量(mini-batch)3d数据组成的4d输入进行批标准化(Batch Normalization)操作，学习参数
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2,stride=2))  # 对于输入信号的输入通道，提供2维最大池化（max pooling）操作；如果输入的大小是(N,C,H,W)，那么输出的大小是(N,C,H_out,W_out)和池化窗口大小

        self.layer2 = nn.Sequential(
            nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=2),  #
            nn.BatchNorm2d(32),  #
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))

        self.fc = nn.Linear(7*7*32, num_classes)  #

    def forward(self, x):
        out = self.layer1(x)
        out = self.layer2(out)
        out = out.reshape(out.size(0), -1) #
        out = self.fc(out)
        return out


model = ConvNet(num_classes).to(device)#

# Loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)

# Train the model
total_step = len(train_loader)
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        images = images.to(device)
        labels = labels.to(device)

        # Forward pass
        outputs = model(images)
        loss = criterion(outputs, labels)

        # Backward and optimize
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if (i+1) % 100 == 0:
            print('Epoch[{} / {}], Step[{} / {}], Loss:{:.4f}'.format(epoch+1, num_epochs, i+1, total_step, loss.item()))


# Test the model
model.eval() # eval mode (batchnorm uses moving mean/variance instead of mini-batch mean/variance)

with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        images = images.to(device)
        labels = labels.to(device)

        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1) #
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

    print('Test Accuracy of the model on the 10000 test images: {} %'.format(100 * correct / total))


# Save the model checkpoint
torch.save(model.state_dict(), 'model.ckpt')  # state_dict (dict) – 保存parameters和persistent buffers的字典。