在pytorch中使用交叉熵损失时，我应该使用softmax作为输出吗? [英] Should I use softmax as output when using cross entropy loss in pytorch?

问题描述

我在对 pytorch 中的 MNIST 数据集的具有 2 个隐藏层的全连接深度神经网络进行分类时遇到问题.

I have a problem with classifying fully connected deep neural net with 2 hidden layers for MNIST dataset in pytorch.

我想在两个隐藏层中都使用 tanh 作为激活函数，但最后我应该使用 softmax.

I want to use tanh as activations in both hidden layers, but in the end, I should use softmax.

对于损失，我在 PyTORch 中选择 nn.CrossEntropyLoss()，它(正如我发现的那样)不想将单热编码标签作为真正的标签，而是采用 LongTensor而不是课程.

For the loss, I am choosing nn.CrossEntropyLoss() in PyTOrch, which (as I have found out) does not want to take one-hot encoded labels as true labels, but takes LongTensor of classes instead.

我的模型是 nn.Sequential() 并且当我最终使用 softmax 时，它在测试数据的准确性方面给了我更糟糕的结果.为什么?

My model is nn.Sequential() and when I am using softmax in the end, it gives me worse results in terms of accuracy on testing data. Why?

import torch
from torch import nn

inputs, n_hidden0, n_hidden1, out = 784, 128, 64, 10
n_epochs = 500
model = nn.Sequential(
    nn.Linear(inputs, n_hidden0, bias=True), 
    nn.Tanh(),
    nn.Linear(n_hidden0, n_hidden1, bias=True),
    nn.Tanh(),
    nn.Linear(n_hidden1, out, bias=True),
    nn.Softmax()  # SHOULD THIS BE THERE?
)
                 
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=0.1, momentum=0.5)

for epoch in range(n_epochs):
    y_pred = model(X_train)
    loss = criterion(y_pred, Y_train)
    print('epoch: ', epoch+1,' loss: ', loss.item())
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()

推荐答案

如中所述torch.nn.CrossEntropyLoss() 文档:

这个标准结合了nn.LogSoftmax() 和 nn.NLLLoss() 合二为一班级.

This criterion combines nn.LogSoftmax() and nn.NLLLoss() in one single class.

因此，您之前应该不要使用 softmax.

Therefore, you should not use softmax before.

这篇关于在pytorch中使用交叉熵损失时，我应该使用softmax作为输出吗?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！