基于pytorh的MNIST手写体识别代码

定义卷积神经网络CNN.py

import torch.nn as nn
import torch.nn.functional as F


class CNN(nn.Module):
    def __init__(self):
        super(CNN,self).__init__()
        self.conv1 = nn.Conv2d(1, 16, kernel_size=5, stride=1, padding=2)
        self.maxpool1 = nn.MaxPool2d(2)
        self.conv2 = nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=2)
        self.maxpool2 = nn.MaxPool2d(2)
        self.fc1 = nn.Linear(32*7*7, 10)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        x = self.maxpool1(x)
        x = F.relu(self.conv2(x))
        x = self.maxpool2(x)
        x = x.view(x.size(0), -1)
        x = self.fc1(x)
        return x

训练代码(使用gpu)：

import torch
import torchvision
import torch.utils.data as Data
from CNN import CNN

DOWNLOAD = False
if __name__ =='__main__':
    train_data=torchvision.datasets.MNIST(
        root='./mnist',
        train=True,
        transform=torchvision.transforms.ToTensor(),
        download=DOWNLOAD,
    )
    cnn = CNN()
    train_loader = Data.DataLoader(dataset=train_data, batch_size=5, shuffle=True)
    test_data = torchvision.datasets.MNIST(root='./mnist/',train=False)
    test_x = torch.unsqueeze(test_data.test_data, dim=1).type(torch.FloatTensor)[:2000] / 255.
    test_y = test_data.test_labels[:2000]
    have_cuda = torch.cuda.is_available()
    if have_cuda:
        cnn.cuda()
        test_x = test_x.cuda()
    optimizer = torch.optim.Adam(cnn.parameters(), lr=0.001)
    loss_func = torch.nn.CrossEntropyLoss()
    for epoch in range(1):
        for step, (b_x, b_y) in enumerate(train_loader):
            if have_cuda:
                b_x = b_x.cuda()
                b_y = b_y.cuda()
            output = cnn(b_x)
            loss = loss_func(output, b_y)
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()
            if step % 50 == 0:
                test_output = cnn(test_x)
                pred_y = torch.max(test_output.cpu(), 1)[1].data.numpy()
                accuracy = float((pred_y == test_y.data.numpy()).astype(int).sum()) / float(test_y.size(0))
                print('Epoch: ', epoch, '| train loss: %.4f' % loss.data.cpu().numpy(),
                      '| test accuracy: %.2f' % accuracy)

    test_output = cnn(test_x[:10])
    pred_y = torch.max(test_output.cpu(), 1)[1].data.numpy()
    print(pred_y, 'prediction number')
    print(test_y[:10].numpy(), 'real number')

训练结果：

Epoch:  0 | train loss: 0.0001 | test accuracy: 0.98
Epoch:  0 | train loss: 0.0043 | test accuracy: 0.98
[7 2 1 0 4 1 4 9 5 9] prediction number
[7 2 1 0 4 1 4 9 5 9] real number