Day 26 - LSTM循環神經網路的實作

14th鐵人賽

dengliu2000

2022-10-10 22:29:30

1916 瀏覽

分享至

以PyTorch進行LSTM循環神經網路的實作

MNIST手寫數據載入

import torch
from torch import nn
from torch.utils.data import DataLoader
import torchvision.datasets as dsets
import torchvision.transforms as transforms

torch.manual_seed(1)

epochs = 5 #訓練數據10次
batch_size = 64
time_step = 28
input_size = 28 
hidden_size = 64
num_layers = 1
num_classes = 10
lr = 0.01 #學習率
DOWNLOAD_MNIST = True
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

train_data = torchvision.datasets.MNIST(
    root='./mnist/',
    train=True,
    transform=torchvision.transforms.ToTensor(),
    download=DOWNLOAD_MNIST
)
test_data = dsets.MNIST(root='./mnist/',
                        train=False,
                        transform=transforms.ToTensor())
train_loader = DataLoader(dataset=train_data,
                          batch_size=batch_size,
                          shuffle=True)
test_loader = DataLoader(dataset=test_data,
                         batch_size=batch_size,
                         shuffle=False)

2.LSTM RNN模型

class simpleLSTM(nn.Module):
    def __init__(self, input_size, hidden_size, num_layers, num_classes):
        super(simpleLSTM, self).__init__()
        self.hidden_size = hidden_size
        self.num_layers = num_layers
        self.lstm = nn.LSTM(input_size, hidden_size, num_layers, batch_first=True)
        self.fc = nn.Linear(hidden_size, num_classes)

    def forward(self, x):
        h0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device)
        c0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device)
        out, (h_n, h_c) = self.lstm(x, (h0, c0))

        out = self.fc(out[:, -1, :])
        return out

model = simpleLSTM(input_size, hidden_size, num_layers, num_classes)

criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr)

3.訓練

total_step = len(train_loader)
for epoch in range(epochs):
    for i, (images, labels) in enumerate(train_loader):
        images = images.reshape(-1, time_step, input_size).to(device)
        labels = labels.to(device)

        outputs = model(images)
        loss = criterion(outputs, labels)

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

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

4.測試模型

model.eval()
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        images = images.reshape(-1, time_step, 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))