LSTM的Pytorch实现

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

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

batch_size=32
device='cpu'
lr=0.01
best_acc=0

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=batch_size, shuffle=True)

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

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

net = net.to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=lr, 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()

        if batch_idx%100==99:
            print('Loss: %.3f | Acc: %.3f%% (%d/%d)'% (train_loss/100, 100.*correct/total, correct, total))
            total = 0
            correct = 0
            train_loss = 0

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()
    acc=correct/total*100.0
    print("Epoch:{},Test loss:{},Test acc:{}".format(epoch,test_loss/total*batch_size,correct/total*100.0))
    if acc>best_acc:
        print("Saving...")
        state={
            "net":net.state_dict(),
            "acc":acc
        }
        torch.save(state,"ckpt.pth")
        best_acc=acc

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