softmax回归pytorch实现代码

Sure, 这是一个简单的 softmax 回归 PyTorch 实现代码：

import torch
import torch.nn as nn
import torch.nn.functional as F

# 定义 softmax 回归模型
class SoftmaxRegression(nn.Module):
    def __init__(self, in_dim, out_dim):
        super(SoftmaxRegression, self).__init__()
        self.linear = nn.Linear(in_dim, out_dim)
    
    def forward(self, x):
        y = self.linear(x)
        y = F.softmax(y, dim=1)
        return y

# 加载数据集
x_train = torch.randn(1000, 10)
y_train = torch.randint(0, 5, (1000,))
x_test = torch.randn(200, 10)
y_test = torch.randint(0, 5, (200,))

# 定义模型、损失函数、优化器
model = SoftmaxRegression(10, 5)
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=0.1)

# 训练模型
for epoch in range(100):
    model.train()
    optimizer.zero_grad()
    y_pred = model(x_train)
    loss = criterion(y_pred, y_train)
    loss.backward()
    optimizer.step()

    # 测试模型
    if epoch % 10 == 0:
        model.eval()
        correct = 0
        with torch.no_grad():
            y_pred = model(x_test)
            _, predicted = torch.max(y_pred, 1)
            correct += (predicted == y_test).sum().item()
        acc = correct / len(y_test)
        print(f"Epoch [{epoch+1}/100], Loss: {loss.item():.4f}, Accuracy: {acc:.4f}")

希望能够帮到你！