参考了网上的一些大神的代码，自己整理了一下程序，在 Pytorch 0.4.0 版本上可以正确运行，现在分享给大家。主要使用torchvision自带的MNIST数据集，进行一个手写字体识别，主要是做了分模块整理和在0.4.0版本的修改，便于理解。

运行环境：Pytorch 0.4.0 CPU版， Python 3.6， Windows7

程序实现：

import torch
import torch.nn as nn
from torch.autograd import Variable
import torch.utils.data as Data
import torchvision
torch.manual_seed(1)

EPOCH = 1
BATCH_SIZE = 50


class CNN(nn.Module):  # 网络结构
    def __init__(self):
        super(CNN, self).__init__()
        self.conv1 = nn.Sequential(nn.Conv2d(in_channels=1, out_channels=16, kernel_size=5, stride=1, padding=2),  # (16,28,28)
                     nn.ReLU(), nn.MaxPool2d(kernel_size=2))
        self.conv2 = nn.Sequential(nn.Conv2d(16, 32, 5, 1, 2), nn.ReLU(), nn.MaxPool2d(2))
        self.out = nn.Linear(32*7*7, 10)

    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        x = x.view(x.size(0), -1)  # 将（batch，32,7,7）展平为（batch，32*7*7）
        output = self.out(x)
        return output


def getData():  # 获取数据
    training_data = torchvision.datasets.MNIST(
        root='./mnist/',  # dataset存储路径
        train=True,  # True表示是train训练集，False表示test测试集
        transform=torchvision.transforms.ToTensor(),  # 将原数据规范化到（0,1）区间
        download=True)  # 获取训练集dataset

    train_loader = Data.DataLoader(dataset=training_data, batch_size=BATCH_SIZE, shuffle=True)  # dataset格式可直接可置于DataLoader

    test_data = torchvision.datasets.MNIST(root='./mnist/', train=False)  # 获取测试集 dataset
    test_x = Variable(torch.unsqueeze(test_data.test_data, dim=1)).type(torch.FloatTensor)[:2000] / 255  # 取前2000个测试集样本
    test_y = test_data.test_labels[:2000]
    return train_loader, test_x, test_y


def trainModel():  # 训练模型
    train_loader, test_x, test_y = getData()
    model = CNN()
    optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
    loss_function = nn.CrossEntropyLoss()

    for epoch in range(EPOCH):
        for step, (x, y) in enumerate(train_loader):

            output = model(x)
            loss = loss_function(output, y)
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()

            if step % 100 == 0:
                test_output = model(test_x)
                pred_y = torch.max(test_output, 1)[1].data.squeeze()
                accuracy = float(sum(pred_y==test_y)) / test_y.size(0)
                print('Epoch:', epoch, '|Step:', step, '|train loss:%.4f' % loss.item(), '|test accuracy:%.4f' % accuracy)

    return model


if __name__ == '__main__':

    model = trainModel()

    # ----------测试--------------
    _, tx, ty = getData()  # 获取数据
    test_output = model(tx[:10])  # 获取预测结果
    py = torch.max(test_output, 1)[1].data.numpy().squeeze()
    print('真实数据：', ty[:10].numpy())
    print('预测结果：', py)

欢迎指正哦