docs/torch/torch.nn/torch.nn.modules/torch.nn.modules.regularization

torch.nn.modules.regularization

Members list

Type members

Classlikes

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 $\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

Value parameters

inplace: – If set to True, will do this operation in-place. Default: false
p: – probability of an element to be zeroed. Default: 0.5

Attributes

See also

See Pytorch C++ Embedding

See Pytorch Python Dropout

See https://pytorch.org/docs/master/nn.html#torch.nn.Dropout

See https://pytorch.org/docs/master/nn.html#torch.nn.Dropout2d

See https://pytorch.org/docs/master/nn.html#torch.nn.Dropout3d

See https://pytorch.org/docs/stable/generated/torch.nn.functional.dropout.html#torch-nn-functional-dropout TODO: https://pytorch.org/docs/master/nn.html#torch.nn.Dropout Add 2D, 3D, Alpha and feature alpha versions

Example

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

Source

Dropout.scala

Supertypes

trait TensorModule[ParamType]

trait Tensor[ParamType] => Tensor[ParamType]

trait HasParams[ParamType]

class Module

class Object

trait Matchable

class Any

Show all

In this article

Generated with