刘二老师第十一讲后半部分在GPU上的代码实现及图像绘制：Residual Network

传送门：第十一讲：高级神经网络

import matplotlib.pyplot as plt
import torch
import torch.nn.functional as F
import torch.optim as optim
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import os
os.environ["KMP_DUPLICATE_LIB_OK"]="True"

# 1.Prepare dataset
batch_size = 64
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307), (0.3081))
])

train_dataset = datasets.MNIST(root="D:\Python-learn\深度学习",
                               train=True,
                               download=False,
                               transform=transform)
train_loader = DataLoader(train_dataset,
                          shuffle=True,
                          batch_size=batch_size)
test_dataset = datasets.MNIST(root="D:\Python-learn\深度学习",
                              train=False,
                              download=False,
                              transform=transform)
test_loader = DataLoader(test_dataset,
                         shuffle=False,
                         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)  # f(x)+x后再激活

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)  # 全连接层

    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()
# 2.1Move model to GPU
device = torch.device("cuda:0"if torch.cuda.is_available() else "cpu")
model.to(device)

# 3. Construcrt Loss and Optimizer
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)

epoch_list = []
right_list = []

# 4.train and test
# Move Tensor To GPU
def train(epoch):
    running_loss = 0.0
    for batch_size, data in enumerate(train_loader,0):
        inputs, target = data
        # 将训练数据转移到GPU
        inputs, target = inputs.to(device), target.to(device)
        optimizer.zero_grad()

        # forward + backward +updata
        outputs = model(inputs)
        loss = criterion(outputs, target)
        loss.backward()
        optimizer.step()
        running_loss += loss.item()
        if batch_size % 300 == 299:
            print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_size + 1, running_loss / 300))
            running_loss = 0.0

def test():
    correct = 0
    total = 0
    with torch.no_grad():
        for data in test_loader:
            images, labels = data
            # 将测试数据转移到GPU
            images, labels = images.to(device), labels.to(device)
            outputs = model(images)
            _, predict = torch.max(outputs.data, dim=1)
            total += labels.size(0)
            correct += (predict == labels).sum().item()
    right_rate = 100 * correct / total
    right_list.append(right_rate)
    print('Accuracy on test set:%d %%' % (right_rate))  # # %%: 用于在字符串中插入一个实际的百分号 %。

if __name__=='__main__':
    for epoch in range(10):
        epoch_list.append(epoch)
        train(epoch)
        test()
    plt.plot(epoch_list, right_list)
    plt.xlabel('Epoch')
    plt.ylabel('Accuracy')
    plt.title('Accuracy vs Epoch')
    plt.show()

运行结果：