为什么会发生此错误。
我正在尝试编写一个自定义损失函数,该函数最终对数可能性为负。
据我了解,NLL是在两个概率值之间计算的?
>>> loss = F.nll_loss(sigm, trg_, ignore_index=250, weight=None, size_average=True)
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/home//lib/python3.5/site-packages/torch/nn/functional.py", line 1332, in nll_loss
return torch._C._nn.nll_loss(input, target, weight, size_average, ignore_index, reduce)
RuntimeError: Expected object of type torch.LongTensor but found type torch.FloatTensor for argument #2 'target'
此处的输入如下:
>>> sigm.size()
torch.Size([151414, 80])
>>> sigm
tensor([[ 0.3283, 0.6472, 0.8278, ..., 0.6756, 0.2168, 0.5659],
[ 0.6603, 0.5957, 0.8375, ..., 0.2274, 0.4523, 0.4665],
[ 0.5262, 0.4223, 0.5009, ..., 0.5734, 0.3151, 0.2076],
...,
[ 0.4083, 0.2479, 0.5996, ..., 0.8355, 0.6681, 0.7900],
[ 0.6373, 0.3771, 0.6568, ..., 0.4356, 0.8143, 0.4704],
[ 0.5888, 0.4365, 0.8587, ..., 0.2233, 0.8264, 0.5411]])
我的目标张量是:
>>> trg_.size()
torch.Size([151414])
>>> trg_
tensor([-7.4693e-01, 3.5152e+00, 2.9679e-02, ..., 1.6316e-01,
3.6594e+00, 1.3366e-01])
如果将其转换为long,则会丢失所有数据:
>>> sigm.long()
tensor([[ 0, 0, 0, ..., 0, 0, 0],
[ 0, 0, 0, ..., 0, 0, 0],
[ 0, 0, 0, ..., 0, 0, 0],
...,
[ 0, 0, 0, ..., 0, 0, 0],
[ 0, 0, 0, ..., 0, 0, 0],
[ 0, 0, 0, ..., 0, 0, 0]])
>>> trg_.long()
tensor([ 0, 3, 0, ..., 0, 3, 0])
如果我也将目标张量的原始值也转换为sigmoid
:
>>> F.sigmoid(trg_)
tensor([ 0.3215, 0.9711, 0.5074, ..., 0.5407, 0.9749, 0.5334])
>>> loss = F.nll_loss(sigm, F.sigmoid(trg_), ignore_index=250, weight=None, size_average=True)
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/home/lib/python3.5/site-packages/torch/nn/functional.py", line 1332, in nll_loss
return torch._C._nn.nll_loss(input, target, weight, size_average, ignore_index, reduce)
RuntimeError: Expected object of type torch.LongTensor but found type torch.FloatTensor for argument #2 'target'
这确实可以很准确地计算出损失,但是由于我在长时间转换中丢失了数据,因此请再次相信:
>>> loss = F.nll_loss(sigm, F.sigmoid(trg_).long(), ignore_index=250, weight=None, size_average=True)
>>> loss
tensor(-0.5010)
>>> F.sigmoid(trg_).long()
tensor([ 0, 0, 0, ..., 0, 0, 0])
答案 0 :(得分:3)
“据我了解,NLL是在两个概率值之间计算的?”
否,不会在两个概率值之间计算NLL。根据{{3}} (请参阅形状部分),通常用于实现交叉熵损失。当N为数据大小且C为类数时,它采用预期为对数概率且大小为(N,C)的输入。目标是一个大小为(N,)的长张量,它说明了样本的真实类别。
由于在您的情况下,确定的目标不是真正的类,所以您可能必须实现自己的损失版本,并且可能无法使用NLLLoss。如果您添加了更多有关您要编码的损失的详细信息,我可以帮助/解释如何执行该损失(如果可能的话,可以使用割炬中的现有功能)。
答案 1 :(得分:2)
我将在此处留下可运行的最少注释代码,使您可以查看每个步骤的尺寸并了解这种(或其他)损失的工作原理:
import torch
import torch.nn as nn
m = nn.LogSoftmax()
loss = nn.NLLLoss()
# input is of size N x C = 3 x 5
# this is FloatTensor containing probability for
# each item in batch for each class
input = torch.randn(3, 5)
# target is LongTensor for index of true class for each item in batch
# each element in target has to have 0 <= value < C
target = torch.tensor([1, 0, 4])
# output is tensor of 0 dimension, i.e., scaler wrapped in tensor
output = loss(m(input), target)