Dropout
torch.nn.``Dropout
(p=0.5, inplace=False)During training,
randomly zeroes
some of the elements of the input tensor with probabilityp
using samples from a Bernoulli distribution`.
- 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 .
[docs]class Dropout(_DropoutNd):
def forward(self, input: Tensor) -> Tensor:
return F.dropout(input, self.p, self.training, self.inplace)