NLLLoss¶
- class
dragon.vm.torch.nn.
NLLLoss
(
weight=None,
size_average=None,
ignore_index=None,
reduce=None,
reduction='mean'
)[source]¶ Compute the negative likelihood loss.
The NLL loss function is defined as:
\[\text{NLLLoss}(p_{t}) = -\log(p_{t}) \]Examples:
m1 = torch.nn.LogSoftmax(dim=1) m2 = torch.nn.NLLLoss() loss = m2(m1(torch.randn(2, 2)), torch.tensor([0, 1]))
See also
__init__¶
NLLLoss.
__init__
(
weight=None,
size_average=None,
ignore_index=None,
reduce=None,
reduction='mean'
)[source]¶Create a
NLLLoss
module.- Parameters:
- weight (dragon.vm.torch.Tensor, optional) – The weight for each class.
- size_average (bool, optional) –
True
to set thereduction
to ‘mean’. - ignore_index (int, optional) – The ignored value of target.
- reduce (bool, optional) –
True
to set thereduction
to ‘sum’ or ‘mean’. - reduction ({'none', 'mean', 'sum', 'valid'}, optional) – The reduce method.