使用循环神经网络做手写数字识别

import torch
from torch import nn
import torchvision.datasets as datasets
import torchvision.transforms as transforms

torch.manual_seed(2019)

# 超参设置
EPOCH = 1  # 训练EPOCH次，这里为了测试方便只跑一次
BATCH_SIZE = 32
TIME_STEP = 28  # RNN时间跨度（图片高度）
INPUT_SIZE = 28  # RNN输入尺寸（图片宽度）
INIT_LR = 0.01  # 初始学习率
DOWNLOAD_MNIST = True  # 设置是否需要下载数据集

# 使用DataLoader加载训练数据，为了演示方便，对于测试数据只取出2000个样本进行测试
train_data = datasets.MNIST(root='mnist', train=True, transform=transforms.ToTensor(), download=DOWNLOAD_MNIST)
train_loader = torch.utils.data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)
test_data = datasets.MNIST(root='mnist', train=False)
test_x = test_data.test_data.type(torch.FloatTensor)[:2000] / 255.
test_y = test_data.test_labels.numpy()[:2000]


class RNN(nn.Module):
    def __init__(self):
        super(RNN, 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_size, time_step, input_size)
        # r_out shape (batch_size, time_step, output_size)
        # h_n shape (n_layers, batch_size, hidden_size)
        # h_c shape (n_layers, batch_size, hidden_size)
        r_out, (h_n, h_c) = self.rnn(x)
        # 取出最后一次循环的r_out传递到全连接层
        out = self.out(r_out[:, -1, :])
        return out


rnn = RNN()
print(rnn)

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

# RNN训练
for epoch in range(EPOCH):
    for step, (b_x, b_y) in enumerate(train_loader):
        # 数据的输入为(batch_size, time_step, input_size)
        b_x = b_x.view(-1, TIME_STEP, INPUT_SIZE)
        output = rnn(b_x)
        loss = loss_func(output, b_y)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if step % 50 == 0:
            prediction = rnn(test_x)  # 输出为(2000, 10)
            pred_y = torch.max(prediction, 1)[1].data.numpy()
            accuracy = (pred_y == test_y).sum() / float(test_y.size)
            print(f'Epoch: [{step}/{epoch}]', f'| train loss: {loss.item()}', f'| test accuracy: {accuracy}')

# 打印测试数据集中的后20个结果
prediction = rnn(test_x[:20].view(-1, 28, 28))
pred_y = torch.max(prediction, 1)[1].data.numpy()
print(pred_y, 'prediction number')
print(test_y[:20], 'real number')