drop_path

dragon.vm.torch.nn.functional.drop_path(
  input,
  p=0.2,
  training=True,
  inplace=False
)[source]

Set the examples over input to zero randomly. [Larsson et.al, 2016].

Parameters:
  • input (dragon.vm.torch.Tensor) The input tensor.
  • p (float, optional, default=0.2) The probability to zero an element.
  • training (bool, optional, default=True) Apply dropping if True.
  • inplace (bool, optional, default=False) Whether to do the operation in-place.
Returns:

dragon.vm.torch.Tensor The output tensor.