Pytorch 单层Bidirectional_Lstm实现MNIST和FashionMNIST数据分类

单层Bidirection_Lstm 实现MNIST和FashionMNIST数据分类

代码实现：

头文件与超参数定义

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

import matplotlib.pyplot as plt
# 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 = 80
num_epochs = 2
learning_rate = 0.003

加载数据集

# MNIST :  '../../dataset/'      FashionMNIST: '../../dataset2/'
train_dataset = torchvision.datasets.FashionMNIST(root='../../dataset2/',
                                           train=True,
                                           transform=transforms.ToTensor(),
                                           download=True)

test_dataset = torchvision.datasets.FashionMNIST(root='../../dataset2/',
                                          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)

定义双层Bidirectional_Lstm模型

# Bidirectional recurrent neural network (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, hidden_size, num_layers, batch_first=True, bidirectional=True)
        self.fc = nn.Linear(hidden_size * 2, num_classes)  # 2 for bidirection

    def forward(self, x):
        # Set initial states
        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)

        # print("h0.shape",h0.shape)
        # print("c0.shape",c0.shape)

        # Forward propagate LSTM
        out, _ = self.lstm(x, (h0, c0))  # out: tensor of shape (batch_size, seq_length, hidden_size*2)
        # print("out.shape",out.shape)
        # print("out[:, -1, :].shape",out[:, -1, :].shape)
        # Decode the hidden state of the last time step
        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)

训练模型
 

# Train the model
total_step = len(train_loader)

print("total_step =",total_step )
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):

        # print("images.shape1",images.shape)

        # 图片可视化
        # plt.text(2, -20, "labels:" + str(labels.numpy()), fontsize=15)
        # grid_img = torchvision.utils.make_grid(images, nrow=10)
        # plt.title("TEST")
        # plt.imshow(grid_img.permute(1, 2, 0))
        # plt.show()


        images = images.reshape(-1, sequence_length, input_size).to(device)
        labels = labels.to(device)
        # print("images.shape2", images.shape)

        # Forward pass
        outputs = model(images)
        # print("outputs.shape1",outputs.shape)

        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()))

测试模型

# 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')