class torch.nn.Dropout(p: float = 0.5, inplace: bool = False) [source]

During training, randomly zeroes some of the elements of the input tensor with probability p using samples from a Bernoulli distribution. Each channel will be zeroed out independently on every forward call.

This has proven to be an effective technique for regularization and preventing the co-adaptation of neurons as described in the paper Improving neural networks by preventing co-adaptation of feature detectors .

Furthermore, the outputs are scaled by a factor of 11p\frac{1}{1-p} during training. This means that during evaluation the module simply computes an identity function.

  • p – probability of an element to be zeroed. Default: 0.5
  • inplace – If set to True, will do this operation in-place. Default: False
  • Input: ()(*) . Input can be of any shape
  • Output: ()(*) . Output is of the same shape as input


>>> m = nn.Dropout(p=0.2)
>>> input = torch.randn(20, 16)
>>> output = m(input)

© 2019 Torch Contributors
Licensed under the 3-clause BSD License.