也许有人能帮我。我试图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]
以及所需的标签,其形式如下
print lab
Variable containing:
x
[torch.FloatTensor of size 1]
其中x是0到9之间的整数。
http://pytorch.org/docs/master/nn.html
)
criterion = nn.CrossEntropyLoss()
loss = criterion(output, lab)
这应该行得通,但不幸的是我出现了一个奇怪的错误
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)
有人能帮我吗?我真的很困惑,尝试了几乎所有我能想象到的有用的东西。
最好的