nn_dropout: Dropout module

nn_dropoutR Documentation

Dropout module

Description

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.

Usage

nn_dropout(p = 0.5, inplace = FALSE)

Arguments

p

probability of an element to be zeroed. Default: 0.5

inplace

If set to TRUE, will do this operation in-place. Default: FALSE.

Details

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 :math:⁠\frac{1}{1-p}⁠ during training. This means that during evaluation the module simply computes an identity function.

Shape

  • Input: (*). Input can be of any shape

  • Output: (*). Output is of the same shape as input

Examples

if (torch_is_installed()) {
m <- nn_dropout(p = 0.2)
input <- torch_randn(20, 16)
output <- m(input)
}

torch documentation built on May 29, 2024, 9:54 a.m.