Lines Matching full:dropout

8     "Dropout",
26                 f"dropout probability has to be between 0 and 1, but got {p}"
35 class Dropout(_DropoutNd):  class
61         >>> m = nn.Dropout(p=0.2)
70         return F.dropout(input, self.p, self.training, self.inplace)
88     (as is normally the case in early convolution layers) then i.i.d. dropout
133     (as is normally the case in early convolution layers) then i.i.d. dropout
146         Due to historical reasons, this class will perform 1D channel-wise dropout
185     (as is normally the case in early convolution layers) then i.i.d. dropout
216     r"""Applies Alpha Dropout over the input.
218     Alpha Dropout is a type of Dropout that maintains the self-normalizing
221     Alpha Dropout maintains the original mean and standard deviation of the
223     Alpha Dropout goes hand-in-hand with SELU activation function, which ensures
263     setting activations to zero, as in regular Dropout, the activations are set
277     (as is normally the case in early convolution layers) then i.i.d. dropout