如何使用pytorch计算softmax回归的成本

import torch
import torch.nn as nn
import torch.optim as optim

class SoftmaxRegression(nn.Module):
    def __init__(self, input_size, num_classes):
        super(SoftmaxRegression, self).__init__()
        self.linear = nn.Linear(input_size, num_classes)
        
    def forward(self, x):
        out = self.linear(x)
        return out

input_size = 10  # 输入特征的维度
num_classes = 3  # 分类的数量
model = SoftmaxRegression(input_size, num_classes)

criterion = nn.CrossEntropyLoss()  # 交叉熵损失函数
optimizer = optim.SGD(model.parameters(), lr=0.01)  # 随机梯度下降优化器

num_epochs = 10  # 迭代次数

for epoch in range(num_epochs):
    # 前向传播
    outputs = model(train_data)
    loss = criterion(outputs, train_labels)
    
    # 反向传播和优化
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()
    
    # 打印训练信息
    if (epoch+1) % 1 == 0:
        print(f'Epoch [{epoch+1}/{num_epochs}], Loss: {loss.item():.4f}')

with torch.no_grad():
    outputs = model(test_data)
    _, predicted = torch.max(outputs.data, 1)