[oneAPI] 手写数字识别-LSTM

比赛：https://marketing.csdn.net/p/f3e44fbfe46c465f4d9d6c23e38e0517
Intel® DevCloud for oneAPI：https://devcloud.intel.com/oneapi/get_started/aiAnalyticsToolkitSamples/

手写数字识别

使用了pytorch以及Intel® Optimization for PyTorch，通过优化扩展了 PyTorch，使英特尔硬件的性能进一步提升，让手写数字识别问题更加的快速高效

使用MNIST数据集，该数据集包含了一系列以黑白图像表示的手写数字，每个图像的大小为28x28像素，数据集组成如下：

• 训练集：包含60,000个图像和标签，用于训练模型。
• 测试集：包含10,000个图像和标签，用于测试模型的性能。

每个图像都被标记为0到9之间的一个数字，表示图像中显示的手写数字。这个数据集常常被用来验证图像分类模型的性能，特别是在计算机视觉领域。

参数与包

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

import intel_extension_for_pytorch as ipex

# Device configuration
device = torch.device('xpu' 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 = 100
num_epochs = 2
learning_rate = 0.01

加载数据

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

test_dataset = torchvision.datasets.MNIST(root='../../data/',
                                          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)

模型

# Recurrent neural network (many-to-one)
class RNN(nn.Module):
    def __init__(self, input_size, hidden_size, num_layers, num_classes):
        super(RNN, 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):
        # Set initial hidden and cell states 
        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)

        # Forward propagate LSTM
        out, _ = self.lstm(x, (h0, c0))  # out: tensor of shape (batch_size, seq_length, hidden_size)

        # Decode the hidden state of the last time step
        out = self.fc(out[:, -1, :])
        return out

训练过程

model = RNN(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)

'''
Apply Intel Extension for PyTorch optimization against the model object and optimizer object.
'''
model, optimizer = ipex.optimize(model, optimizer=optimizer)

# Train the model
total_step = len(train_loader)
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        images = images.reshape(-1, sequence_length, input_size).to(device)
        labels = labels.to(device)

        # Forward pass
        outputs = model(images)
        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()))

# Test the model
model.eval()
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')

结果

oneAPI

import intel_extension_for_pytorch as ipex

# Device configuration
device = torch.device('xpu' if torch.cuda.is_available() else 'cpu')

# 模型
model = ConvNet(num_classes).to(device)

# Loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)

'''
Apply Intel Extension for PyTorch optimization against the model object and optimizer object.
'''
model, optimizer = ipex.optimize(model, optimizer=optimizer)