卷积神经网络CNN MNIST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 InceptionA(torch.nn.Module):
    def __init__(self, in_channels):
        super(InceptionA, self).__init__()
        self.branch1x1 = torch.nn.Conv2d(in_channels, 16, kernel_size=1)

        self.branch5x5_1 = torch.nn.Conv2d(in_channels, 16, kernel_size=1)
        self.branch5x5_2 = torch.nn.Conv2d(16, 24, kernel_size=5, padding=2)

        self.branch3x3_1 = torch.nn.Conv2d(in_channels, 16, kernel_size=1)
        self.branch3x3_2 = torch.nn.Conv2d(16, 24, kernel_size=3, padding=1)
        self.branch3x3_3 = torch.nn.Conv2d(24, 24, kernel_size=3, padding=1)

        self.branch_pool = torch.nn.Conv2d(in_channels, 24, kernel_size=1)

    def forward(self, x):
        branch1x1 = self.branch1x1(x)

        branch5x5 = self.branch5x5_1(x)
        branch5x5 = self.branch5x5_2(branch5x5)

        branch3x3 = self.branch3x3_1(x)
        branch3x3 = self.branch3x3_2(branch3x3)
        branch3x3 = self.branch3x3_3(branch3x3)

        branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1)
        branch_pool = self.branch_pool(branch_pool)

        outputs = [branch1x1, branch5x5, branch3x3, branch_pool]
        return torch.cat(outputs, dim=1)


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(88, 20, kernel_size=5)

        self.incept1 = InceptionA(in_channels=10)
        self.incept2 = InceptionA(in_channels=20)

        self.mp = torch.nn.MaxPool2d(2)
        self.fc = torch.nn.Linear(1408, 10)

    def forward(self, x):
        in_size = x.size(0)
        x = F.relu(self.mp(self.conv1(x)))
        x = self.incept1(x)
        x = F.relu(self.mp(self.conv2(x)))
        x = self.incept2(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: 0.874
[1, 600] loss: 0.230
[1, 900] loss: 0.147
Accuracy on test set: 95 %
[2, 300] loss: 0.118
[2, 600] loss: 0.105
[2, 900] loss: 0.088
Accuracy on test set: 97 %
[3, 300] loss: 0.084
[3, 600] loss: 0.073
[3, 900] loss: 0.071
Accuracy on test set: 97 %
[4, 300] loss: 0.068
[4, 600] loss: 0.062
[4, 900] loss: 0.061
Accuracy on test set: 98 %
[5, 300] loss: 0.054
[5, 600] loss: 0.054
[5, 900] loss: 0.057
Accuracy on test set: 98 %
[6, 300] loss: 0.047
[6, 600] loss: 0.051
[6, 900] loss: 0.052
Accuracy on test set: 98 %
[7, 300] loss: 0.049
[7, 600] loss: 0.041
[7, 900] loss: 0.046
Accuracy on test set: 98 %
[8, 300] loss: 0.047
[8, 600] loss: 0.040
[8, 900] loss: 0.038
Accuracy on test set: 98 %
[9, 300] loss: 0.037
[9, 600] loss: 0.041
[9, 900] loss: 0.040
Accuracy on test set: 98 %
[10, 300] loss: 0.033
[10, 600] loss: 0.035
[10, 900] loss: 0.040
Accuracy on test set: 98 %