PyTorch：RNN网络训练MNIST数据集

import torch
from torch import nn
import torchvision.datasets as dsets
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
import os


# Hyper Parameters
EPOCH = 10
BATCH_SIZE = 64
INPUT_SIZE = 28 
LR = 0.01
DOWNLOAD_MNIST = False


class RNNnet(nn.Module):
    def __init__(self):
        super(RNNnet, self).__init__()
        self.rnn = nn.LSTM(
            input_size=INPUT_SIZE,
            hidden_size=64,  
            num_layers=1,
            batch_first=True
        )
        self.out = nn.Linear(64, 10)

    def forward(self, x):
        # x shape (batch, time_step, input_size)
        # r_out shape (batch, time_step, output_size)
        # h_n shape (n_layers, batch, hidden_size)
        # h_c shape (n_layers, batch, hidden_size)
        r_out, (h_n, h_c) = self.rnn(x, None)
        # choose r_out at the last time step
        out = self.out(r_out[:, -1, :])
        return out


if __name__ == '__main__':
    # Mnist digits dataset
    if not (os.path.exists('./mnist/')) or not os.listdir('./mnist/'):
        DOWNLOAD_MNIST = True

	# 加载训练数据
    train_data = dsets.MNIST(
        root='./mnist/',
        train=True,
        transform=transforms.ToTensor(),
        download=DOWNLOAD_MNIST
    )

    # plot one example
    print(train_data.data.size())     # (60000, 28, 28)
    print(train_data.targets.size())   # (60000)
    plt.imshow(train_data.data[0].numpy(), cmap='gray')
    plt.title('%i' % train_data.targets[0])
    plt.show()

    train_loader = torch.utils.data.DataLoader(
        dataset=train_data,
        batch_size=BATCH_SIZE,
        shuffle=True
    )
	
	# 加载测试数据
    test_data = dsets.MNIST(root='./mnist/',
                            train=False,
                            transform=transforms.ToTensor()
                            )
    test_x = test_data.data.type(torch.FloatTensor)[:2000]/255.
    test_y = test_data.targets.numpy()[:2000]

    rnn = RNNnet()
    print(rnn)

    optimizer = torch.optim.Adam(rnn.parameters(), lr=LR)
    loss_func = nn.CrossEntropyLoss()

    # training and testing
    for epoch in range(EPOCH):
        for step, (b_x, b_y) in enumerate(train_loader)
            b_x = b_x.view(-1, 28, 28) 
            output = rnn(b_x)
            loss = loss_func(output, b_y)
            optimizer.zero_grad()
            loss.backward()
            optimizer.step() 

            if step % 50 == 0:
                test_output = rnn(test_x)
                pred_y = torch.max(test_output, 1)[1].data.numpy()
                accuracy = float((pred_y == test_y).astype(int).sum()) / float(test_y.size)
                print('Epoch: ', epoch, '| train loss: %.4f' % loss.data.numpy(), '| test accuracy: %.2f' % accuracy)

    # print 10 predictions from test data
    test_output = rnn(test_x[:10].view(-1, 28, 28))
    pred_y = torch.max(test_output, 1)[1].data.numpy()
    print(pred_y, 'prediction number')
    print(test_y[:10], 'real number')

morvan视频有更详细的介绍