PyTorch入门二：LSTM实现MNIST手写数字识别

飞熊 • 2023年9月5日下午6:58 • Python • 阅读 114

参考博客：https://blog.csdn.net/winycg/article/details/88937583

LSTM(Long Short Term Memory)，长短时记忆网络，主要用于传统RNN网络所面临的梯度消失/爆炸等问题。关于LSTM的基本原理可以参考我的另外一篇博客：RNN神经网络

nn.LSTM

LSTM实现MNIST分类

MNIST图片大小为28×28，可以将每张图片看做是长为28的序列，序列中每个元素的特征维度为28。将最后输出的隐藏状态

h_T

$h_{T}$ 作为抽象的隐藏特征输入到全连接层进行分类。

导入基础包

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

定义网络结构

class Rnn(nn.Module):
    def __init__(self, in_dim, hidden_dim, n_layer, n_classes):
        super(Rnn, self).__init__()
        self.n_layer = n_layer
        self.hidden_dim = hidden_dim
        self.lstm = nn.LSTM(in_dim, hidden_dim, n_layer, batch_first=True)
        self.classifier = nn.Linear(hidden_dim, n_classes)

    def forward(self, x):
        out, (h_n, c_n) = self.lstm(x)
        # 此时可以从out中获得最终输出的状态h
        # x = out[:, -1, :]
        x = h_n[-1, :, :]
        x = self.classifier(x)
        return x

训练和测试

transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize([0.5], [0.5]),
])

trainset = torchvision.datasets.MNIST(root='./data', train=True, download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=128, shuffle=True)

testset = torchvision.datasets.MNIST(root='./data', train=False, download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=100, shuffle=False)

net = Rnn(28, 10, 2, 10)

net = net.to('cpu')
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.1, momentum=0.9)

# Training
def train(epoch):
    print('\nEpoch: %d' % epoch)
    net.train()
    train_loss = 0
    correct = 0
    total = 0
    for batch_idx, (inputs, targets) in enumerate(trainloader):
        inputs, targets = inputs.to('cpu'), targets.to('cpu')
        optimizer.zero_grad()
        outputs = net(torch.squeeze(inputs, 1))
        loss = criterion(outputs, targets)
        loss.backward()
        optimizer.step()

        train_loss += loss.item()
        _, predicted = outputs.max(1)
        total += targets.size(0)
        correct += predicted.eq(targets).sum().item()

        print(batch_idx, len(trainloader), 'Loss: %.3f | Acc: %.3f%% (%d/%d)'
            % (train_loss/(batch_idx+1), 100.*correct/total, correct, total))

def test(epoch):
    global best_acc
    net.eval()
    test_loss = 0
    correct = 0
    total = 0
    with torch.no_grad():
        for batch_idx, (inputs, targets) in enumerate(testloader):
            inputs, targets = inputs.to('cpu'), targets.to('cpu')
            outputs = net(torch.squeeze(inputs, 1))
            loss = criterion(outputs, targets)

            test_loss += loss.item()
            _, predicted = outputs.max(1)
            total += targets.size(0)
            correct += predicted.eq(targets).sum().item()

            print(batch_idx, len(testloader), 'Loss: %.3f | Acc: %.3f%% (%d/%d)'
                % (test_loss/(batch_idx+1), 100.*correct/total, correct, total))




for epoch in range(200):
    train(epoch)
    test(epoch)