pytorch学习笔记系列（6）：循环神经网络和双向循环神经网络---MNIST数据集

Pytorch中LSTM的定义如下：

class torch.nn.LSTM(*args, **kwargs)

参数列表

• input_size：x的特征维度
• hidden_size：隐藏层的特征维度
• num_layers：lstm隐层的层数，默认为1
• bias：False则$b_{ih}=0$和$b_{hh}=0$. 默认为True
• batch_first：True则输入输出的数据格式为 (batch, seq, feature)
• dropout：除最后一层，每一层的输出都进行dropout，默认为: 0
• bidirectional：True则为双向lstm默认为False
• 输入：input, ($h_0$, $c_0$)
• 输出：output, ($h_n$,$c_n$)

---

使用Bi-LSTM来训练MNIST数据集

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

# Device configuration
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

# Hyper-parameters
sequence_length = 28
input_size = 28
hidden_size = 128
num_layers = 2
num_classes = 10
batch_size = 100
num_epochs = 2
learning_rate = 0.003

# MNIST dataset
train_dataset = torchvision.datasets.MNIST(root='../../data/',
                                           train=True,
                                           transform=transforms.ToTensor(),
                                           download=True)

test_dataset = torchvision.datasets.MNIST(root='../../data/',
                                          train=False,
                                          transform=transforms.ToTensor())

# Data loader
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
                                           batch_size=batch_size,
                                           shuffle=True)

test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
                                          batch_size=batch_size,
                                          shuffle=False)


# 双向循环神经网络 (many-to-one)
class BiRNN(nn.Module):
    def __init__(self, input_size, hidden_size, num_layers, num_classes):
        super(BiRNN, self).__init__()
        self.hidden_size = hidden_size
        self.num_layers = num_layers
        self.lstm = nn.LSTM(input_size,# x的特征维度
                            hidden_size,# 隐藏层单元数
                            num_layers,# 层数
                            batch_first=True,# 第一个维度设为 batch, 即:(batch_size, seq_length, input_size)
                            bidirectional=True) # 是否用双向
        self.fc = nn.Linear(hidden_size * 2, num_classes)  # 2 for bidirection

    def forward(self, x):
        # x维度为(batch_size, time_step, input_size)
        # 隐层初始化
        # h0维度为(num_layers*direction_num, batch_size, hidden_size)
        # c0维度为(num_layers*direction_num, batch_size, hidden_size)
        h0 = torch.zeros(self.num_layers * 2, x.size(0), self.hidden_size).to(device)  # 2 for bidirection
        c0 = torch.zeros(self.num_layers * 2, x.size(0), self.hidden_size).to(device)

        # LSTM前向传播，此时out维度为(batch_size, seq_length, hidden_size*2)
        # hn,cn表示最后一个状态?维度与h0和c0一样
        out, (hn, cn) = self.lstm(x, (h0, c0))

        # 我们只需要最后一步的输出,即(batch_size, -1, output_size)
        out = self.fc(out[:, -1, :])
        return out


model = BiRNN(input_size, hidden_size, num_layers, num_classes).to(device)

# Loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)

# Train the model
total_step = len(train_loader)
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        images = images.reshape(-1, sequence_length, input_size).to(device)
        labels = labels.to(device)

        # Forward pass
        outputs = model(images)
        loss = criterion(outputs, labels)

        # Backward and optimize
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if (i + 1) % 100 == 0:
            print('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'
                  .format(epoch + 1, num_epochs, i + 1, total_step, loss.item()))

# Test the model
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        images = images.reshape(-1, sequence_length, input_size).to(device)
        labels = labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

    print('Test Accuracy of the model on the 10000 test images: {} %'.format(100 * correct / total))

# Save the model checkpoint
torch.save(model.state_dict(), 'model.ckpt')