pytorch 中的交叉熵损失 nn.CrossEntropyLoss()

Question

也许有人可以帮助我。我正在尝试计算网络给定输出的交叉熵损失

print output
Variable containing:
1.00000e-02 *
-2.2739  2.9964 -7.8353  7.4667  4.6921  0.1391  0.6118  5.2227  6.2540     
-7.3584
[torch.FloatTensor of size 1x10]

和所需的标签，格式为

print lab
Variable containing:
x
[torch.FloatTensor of size 1]

其中 x 是 0 到 9 之间的整数。根据 pytorch 文档 (http://pytorch.org/docs/master/nn.html)

criterion = nn.CrossEntropyLoss()
loss = criterion(output, lab)

这应该可以，但不幸的是我收到一个奇怪的错误

TypeError: FloatClassNLLCriterion_updateOutput received an invalid combination of arguments - got (int, torch.FloatTensor, !torch.FloatTensor!, torch.FloatTensor, bool, NoneType, torch.FloatTensor, int), but expected (int state, torch.FloatTensor input, torch.LongTensor target, torch.FloatTensor output, bool sizeAverage, [torch.FloatTensor weights or None], torch.FloatTensor total_weight, int ignore_index)

谁能帮帮我？我真的很困惑，几乎尝试了所有我能想到的有用的东西。

最佳

Answer 1

请检查此代码

import torch
import torch.nn as nn
from torch.autograd import Variable

output = Variable(torch.rand(1,10))
target = Variable(torch.LongTensor([1]))

criterion = nn.CrossEntropyLoss()
loss = criterion(output, target)
print(loss)

这将很好地打印出损失：

Variable containing:
 2.4498
[torch.FloatTensor of size 1]

pytorch 中的交叉熵损失 nn.CrossEntropyLoss()

Cross entropy loss in pytorch nn.CrossEntropyLoss()

entropy

loss

torch

cross-entropy

pytorch