BCEWithLogitsLoss¶
- class
dragon.vm.torch.nn.
BCEWithLogitsLoss
(
weight=None,
size_average=None,
reduce=None,
reduction='mean',
pos_weight=None
)[source]¶ Compute the sigmoid cross entropy.
Examples:
m = torch.nn.BCEWithLogitsLoss() loss = m(torch.randn(2, 1), torch.tensor([0., 1.], 'float32'))
__init__¶
BCEWithLogitsLoss.
__init__
(
weight=None,
size_average=None,
reduce=None,
reduction='mean',
pos_weight=None
)[source]¶Create a
BCEWithLogitsLoss
module.- Parameters:
- weight (dragon.vm.torch.Tensor, optional) – The weight for each class.
- size_average (bool, optional) –
True
to set thereduction
to ‘mean’. - reduce (bool, optional) –
True
to set thereduction
to ‘sum’ or ‘mean’. - reduction ({'none', 'mean', 'sum', 'valid'}, optional) – The reduce method.