卷积神经网络CNN MNIST Residual高级版

import numpy as np
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
import matplotlib.pyplot as plt

accuracy_list =[]
epoch_list = []


# prepare dta
batch_size = 64
# convert PIL image to Tensor
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 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()
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()

        # forward + backward + update
        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 / 300))
            running_loss = 0.0



# test
def test():
    correct = 0
    total = 0
    with torch.no_grad():
        for data in test_loader:
            images, labels = data
            images, labels = images.to(device), labels.to(device)
            outputs = model(images)
            _, 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))
    accuracy_list.append(100 * correct / total)


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

        epoch_list.append(epoch)


# 绘图
plt.plot(epoch_list, accuracy_list)
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.show()

结果：

[1, 300] loss: 0.608
[1, 600] loss: 0.159
[1, 900] loss: 0.115
Accuracy on test set: 97 %
[2, 300] loss: 0.084
[2, 600] loss: 0.081
[2, 900] loss: 0.074
Accuracy on test set: 97 %
[3, 300] loss: 0.060
[3, 600] loss: 0.057
[3, 900] loss: 0.055
Accuracy on test set: 98 %
[4, 300] loss: 0.046
[4, 600] loss: 0.050
[4, 900] loss: 0.047
Accuracy on test set: 98 %
[5, 300] loss: 0.041
[5, 600] loss: 0.037
[5, 900] loss: 0.040
Accuracy on test set: 98 %
[6, 300] loss: 0.033
[6, 600] loss: 0.034
[6, 900] loss: 0.036
Accuracy on test set: 98 %
[7, 300] loss: 0.032
[7, 600] loss: 0.028
[7, 900] loss: 0.032
Accuracy on test set: 98 %
[8, 300] loss: 0.025
[8, 600] loss: 0.028
[8, 900] loss: 0.026
Accuracy on test set: 98 %
[9, 300] loss: 0.023
[9, 600] loss: 0.024
[9, 900] loss: 0.027
Accuracy on test set: 98 %
[10, 300] loss: 0.022
[10, 600] loss: 0.021
[10, 900] loss: 0.022
Accuracy on test set: 98 %