PyTorch实战案例（四）——利用PyTorch实现循环神经网络RNN算法对mnist数据集分类

一、案例描述

本文将介绍利用PyTorch实现循环神经网络RNN算法对mnist手写数字数据集进行分类。

二、代码详解

2.1 加载数据集

加载mnist训练集和测试集，选取2000个样本以加快测试速度：

# Hyper Parameters
EPOCH = 1               # train the training data n times, to save time, we just train 1 epoch
BATCH_SIZE = 64
TIME_STEP = 28          # rnn time step / image height
INPUT_SIZE = 28         # rnn input size / image width
LR = 0.01               # learning rate
DOWNLOAD_MNIST = True   # set to True if haven't download the data

# Mnist digital dataset
train_data = torchvision.datasets.MNIST(
    root='./mnist/',
    train=True,                         # this is training data
    transform=transforms.ToTensor(),    # Converts a PIL.Image or numpy.ndarray to
                                        # torch.FloatTensor of shape (C x H x W) and normalize in the range [0.0, 1.0]
    download=DOWNLOAD_MNIST,            # download it if you don't have it
)
print(train_data.train_data.size())     # (60000, 28, 28)
print(train_data.train_labels.size())   # (60000)

# 加载训练数据集
train_loader = torch.utils.data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)

# 加载测试数据集,选取2000个样本以加快测试速度
test_data = torchvision.datasets.MNIST(root='./mnist/', train=False, transform=transforms.ToTensor())
test_x = test_data.test_data.type(torch.FloatTensor)[:2000]/255.   # shape (2000, 28, 28) value in range(0,1)
test_y = test_data.test_labels.numpy()[:2000]    # covert to numpy array

2.2 定义模型

定义RNN网络结构，一个LSTM层和一个线性输出层组成：

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, 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)   # None represents zero initial hidden state

        # choose r_out at the last time step
        out = self.out(r_out[:, -1, :])
        return out

rnn = RNN()
print(rnn)

运行结果：
RNN(
(rnn): LSTM(28, 64, batch_first=True)
(out): Linear(in_features=64, out_features=10, bias=True)
)

2.3 开始训练

设置优化器和损失函数：

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

开始训练：

# 训练
for epoch in range(EPOCH):
    for step, (b_x, b_y) in enumerate(train_loader):        # gives batch data
        b_x = b_x.view(-1, 28, 28)              # reshape x to (batch, time_step, input_size)

        output = rnn(b_x)                               # rnn output
        loss = loss_func(output, b_y)                   # cross entropy loss
        optimizer.zero_grad()                           # clear gradients for this training step
        loss.backward()                                 # backpropagation, compute gradients
        optimizer.step()                                # apply gradients
		# 每迭代50次计算一次测试集准确率
        if step % 50 == 0:
            test_output = rnn(test_x)                   # (samples, time_step, input_size)
            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)

2.4 测试准确率

打印输出测试数据的预测结果和真实结果：

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')

运行结果如下：

三、完整代码

完整代码如下：

import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms

# Hyper Parameters
EPOCH = 1               # train the training data n times, to save time, we just train 1 epoch
BATCH_SIZE = 64
TIME_STEP = 28          # rnn time step / image height
INPUT_SIZE = 28         # rnn input size / image width
LR = 0.01               # learning rate
DOWNLOAD_MNIST = True   # set to True if haven't download the data

# Mnist digital dataset
train_data = torchvision.datasets.MNIST(
    root='./mnist/',
    train=True,                         # this is training data
    transform=transforms.ToTensor(),    # Converts a PIL.Image or numpy.ndarray to
                                        # torch.FloatTensor of shape (C x H x W) and normalize in the range [0.0, 1.0]
    download=DOWNLOAD_MNIST,            # download it if you don't have it
)
print(train_data.train_data.size())     # (60000, 28, 28)
print(train_data.train_labels.size())   # (60000)

# 加载训练数据集
train_loader = torch.utils.data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)

# 加载测试数据集,选取2000个样本以加快测试速度
test_data = torchvision.datasets.MNIST(root='./mnist/', train=False, transform=transforms.ToTensor())
test_x = test_data.test_data.type(torch.FloatTensor)[:2000]/255.   # shape (2000, 28, 28) value in range(0,1)
test_y = test_data.test_labels.numpy()[:2000]    # covert to numpy array


class RNN(nn.Module):
    def __init__(self):
        super(RNN, self).__init__()

        self.rnn = nn.LSTM(         # if use nn.RNN(), it hardly learns
            input_size=INPUT_SIZE,
            hidden_size=64,         # rnn hidden unit
            num_layers=1,           # number of rnn layer
            batch_first=True,       # input & output will has batch size as 1s dimension. e.g. (batch, time_step, input_size)
        )
        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)   # None represents zero initial hidden state

        # choose r_out at the last time step
        out = self.out(r_out[:, -1, :])
        return out


rnn = RNN()
print(rnn)

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

# 训练
for epoch in range(EPOCH):
    for step, (b_x, b_y) in enumerate(train_loader):        # gives batch data
        b_x = b_x.view(-1, 28, 28)              # reshape x to (batch, time_step, input_size)

        output = rnn(b_x)                               # rnn output
        loss = loss_func(output, b_y)                   # cross entropy loss
        optimizer.zero_grad()                           # clear gradients for this training step
        loss.backward()                                 # backpropagation, compute gradients
        optimizer.step()                                # apply gradients

        if step % 50 == 0:
            test_output = rnn(test_x)                   # (samples, time_step, input_size)
            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')

---

ok，以上便是本文的全部内容了，看完了之后记得一定要亲自独立动手实践一下呀~