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')