Task 04：关于softmax问题

问题所属任务编号（Task 01-05）

Task 04

第一个问题：
nn.Sequential里面没有softmax层，是不是计算交叉熵的时候包含了，也就是nn.CrossEntropyLoss()封装了softmax层？

第二个问题：

def evaluate_accuracy(net, data_iter): #@save
    if isinstance(net, torch.nn.Module):
        net.eval()
    metric = Accumulator(2)
    with torch.no_grad():
        for X,y in data_iter:
            metric.add(accuracy(net(X),y),y.numel())
        return metric[0]/metric[1]

在评估测试集正确率的时候，我们已经进入了net.eval()评估模式，不在更新参数，为什么还要with torch.no_grad():，是否必须加

关于第一个问题请参考 #39
第二个问题其实也在 Pytorch 官方文档中有详细说明

我们推荐将每个问题分为独立的 issue 进行讨论，也请仔细阅读 学习者手册中的提问部分，RTFM

Deleting a branch is permanent. It CANNOT be undone. Continue?

Dear OpenI User

Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.

For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》

#45 Task 04：关于softmax问题

问题所属任务编号（Task 01-05）