PyTorch实战-手写数字识别-单层感知机

1 需求

2 接口

3 示例

import torch
import torch.nn as nn
import torchvision.datasets as datasets
import torchvision.transforms as transforms
from torch.utils.data import DataLoader# 定义超参数
batch_size = 64
learning_rate = 0.01
num_epochs = 10# 数据预处理
transform = transforms.Compose([transforms.ToTensor(),transforms.Normalize((0.1307,), (0.3081,))
])# 加载MNIST数据集
train_dataset = datasets.MNIST(root='./data', train=True, transform=transform, download=True)
test_dataset = datasets.MNIST(root='./data', train=False, transform=transform, download=True)train_loader = DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=True)
test_loader = DataLoader(dataset=test_dataset, batch_size=batch_size, shuffle=False)# 定义单层感知机模型
class SingleLayerPerceptron(nn.Module):def __init__(self):super(SingleLayerPerceptron, self).__init__()self.fc = nn.Linear(784, 10)def forward(self, x):x = x.view(-1, 784)out = self.fc(x)return out# 实例化模型
model = SingleLayerPerceptron()# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)# 训练模型
for epoch in range(num_epochs):for batch_idx, (data, targets) in enumerate(train_loader):# 前向传播outputs = model(data)loss = criterion(outputs, targets)# 反向传播和优化optimizer.zero_grad()loss.backward()optimizer.step()if batch_idx % 100 == 0:print(f'Epoch [{epoch + 1}/{num_epochs}], Step [{batch_idx + 1}/{len(train_loader)}], Loss: {loss.item()}')# 在测试集上评估模型
model.eval()
with torch.no_grad():correct = 0total = 0for data, targets in test_loader:outputs = model(data)_, predicted = torch.max(outputs.data, 1)total += targets.size(0)correct += (predicted == targets).sum().item()accuracy = correct / totalprint(f'Test Accuracy: {accuracy * 100:.2f}%')