我一直在尝试在Pytorch中使用LSTM(在自定义模型中在LSTM之后是线性层),但是在计算损耗时遇到了以下错误:
Assertion cur_target >= 0 && cur_target < n_classes' failed.
我用以下方法定义了损失函数:
criterion = nn.CrossEntropyLoss()
然后用
调用loss += criterion(output, target)
我给目标的尺寸为[sequence_length,number_of_classes],输出的尺寸为[sequence_length,1,number_of_classes]。
我遵循的示例似乎在做同样的事情,但是在Pytorch docs on cross entropy loss.
上却有所不同文档说目标应该是维度(N),其中每个值是0≤target [i]≤C-1,C是类数。我将目标更改为这种形式,但是现在我得到一个错误提示(序列长度为75,并且有55个类):
Expected target size (75, 55), got torch.Size([75])
我尝试着寻找两种错误的解决方案,但仍然无法正常工作。我对目标的正确尺寸以及第一个错误的实际含义感到困惑(不同的搜索给出的错误含义非常不同,没有一个修复程序起作用)。
谢谢
答案 0 :(得分:3)
您可以在squeeze()
张量上使用output
,这将返回一个已删除尺寸为1的所有尺寸的张量。
此短代码使用您在问题中提到的形状:
sequence_length = 75
number_of_classes = 55
# creates random tensor of your output shape
output = torch.rand(sequence_length, 1, number_of_classes)
# creates tensor with random targets
target = torch.randint(55, (75,)).long()
# define loss function and calculate loss
criterion = nn.CrossEntropyLoss()
loss = criterion(output, target)
print(loss)
导致您描述的错误:
ValueError: Expected target size (75, 55), got torch.Size([75])
因此,在squeeze()
张量上使用output
可以通过使其形状正确来解决您的问题。
形状正确的示例:
sequence_length = 75
number_of_classes = 55
# creates random tensor of your output shape
output = torch.rand(sequence_length, 1, number_of_classes)
# creates tensor with random targets
target = torch.randint(55, (75,)).long()
# define loss function and calculate loss
criterion = nn.CrossEntropyLoss()
# apply squeeze() on output tensor to change shape form [75, 1, 55] to [75, 55]
loss = criterion(output.squeeze(), target)
print(loss)
输出:
tensor(4.0442)
使用squeeze()
将张量形状从[75, 1, 55]
更改为[75, 55]
,以使输出形状和目标形状匹配!
您还可以使用其他方法来重塑张量,这很重要,您的形状应为[sequence_length, number_of_classes]
而不是[sequence_length, 1, number_of_classes]
。
您的目标应为LongTensor
。包含类的torch.long
类型的张量。形状为[sequence_length]
。
编辑:
传递给交叉熵函数时,上述示例的形状:
输出:torch.Size([75, 55])
目标:torch.Size([75])
这是一个更通用的示例,CE的输出和目标应为什么样。在这种情况下,我们假设有5种不同的目标类别,对于长度为1、2和3的序列,有3个示例。
# init CE Loss function
criterion = nn.CrossEntropyLoss()
# sequence of length 1
output = torch.rand(1, 5)
# in this case the 1th class is our target, index of 1th class is 0
target = torch.LongTensor([0])
loss = criterion(output, target)
print('Sequence of length 1:')
print('Output:', output, 'shape:', output.shape)
print('Target:', target, 'shape:', target.shape)
print('Loss:', loss)
# sequence of length 2
output = torch.rand(2, 5)
# targets are here 1th class for the first element and 2th class for the second element
target = torch.LongTensor([0, 1])
loss = criterion(output, target)
print('\nSequence of length 2:')
print('Output:', output, 'shape:', output.shape)
print('Target:', target, 'shape:', target.shape)
print('Loss:', loss)
# sequence of length 3
output = torch.rand(3, 5)
# targets here 1th class, 2th class and 2th class again for the last element of the sequence
target = torch.LongTensor([0, 1, 1])
loss = criterion(output, target)
print('\nSequence of length 3:')
print('Output:', output, 'shape:', output.shape)
print('Target:', target, 'shape:', target.shape)
print('Loss:', loss)
输出:
Sequence of length 1:
Output: tensor([[ 0.1956, 0.0395, 0.6564, 0.4000, 0.2875]]) shape: torch.Size([1, 5])
Target: tensor([ 0]) shape: torch.Size([1])
Loss: tensor(1.7516)
Sequence of length 2:
Output: tensor([[ 0.9905, 0.2267, 0.7583, 0.4865, 0.3220],
[ 0.8073, 0.1803, 0.5290, 0.3179, 0.2746]]) shape: torch.Size([2, 5])
Target: tensor([ 0, 1]) shape: torch.Size([2])
Loss: tensor(1.5469)
Sequence of length 3:
Output: tensor([[ 0.8497, 0.2728, 0.3329, 0.2278, 0.1459],
[ 0.4899, 0.2487, 0.4730, 0.9970, 0.1350],
[ 0.0869, 0.9306, 0.1526, 0.2206, 0.6328]]) shape: torch.Size([3, 5])
Target: tensor([ 0, 1, 1]) shape: torch.Size([3])
Loss: tensor(1.3918)
我希望这会有所帮助!