[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 transformsimport 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_sizeself.num_layers = num_layersself.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 LSTMout, _ = self.lstm(x, (h0, c0))  # out: tensor of shape (batch_size, seq_length, hidden_size)# Decode the hidden state of the last time stepout = 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 passoutputs = model(images)loss = criterion(outputs, labels)# Backward and optimizeoptimizer.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 = 0total = 0for 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)