Dropout — mlr_pipeops_nn_dropout • mlr3torch

During training, randomly zeroes some of the elements of the input tensor with probability p using samples from a Bernoulli distribution.

nn_module

Calls torch::nn_dropout() when trained.

Parameters

p :: numeric(1)
Probability of an element to be zeroed. Default: 0.5.
inplace :: logical(1)
If set to TRUE, will do this operation in-place. Default: FALSE.

Input and Output Channels

One input channel called "input" and one output channel called "output". For an explanation see PipeOpTorch.

State

The state is the value calculated by the public method $shapes_out().

Super classes

mlr3pipelines::PipeOp -> PipeOpTorch -> PipeOpTorchDropout

Methods

Inherited methods

`PipeOpTorchDropout$new()`

Creates a new instance of this R6 class.

Usage

PipeOpTorchDropout$new(id = "nn_dropout", param_vals = list())

Arguments

id: (character(1))
Identifier of the resulting object.
param_vals: (list())
List of hyperparameter settings, overwriting the hyperparameter settings that would otherwise be set during construction.

`PipeOpTorchDropout$clone()`

The objects of this class are cloneable with this method.

Usage

PipeOpTorchDropout$clone(deep = FALSE)

Arguments

deep: Whether to make a deep clone.

Examples

# Construct the PipeOp
pipeop = nn("dropout")
pipeop
#> 
#> ── PipeOp <dropout>: not trained ───────────────────────────────────────────────
#> Values: list()
#> 
#> ── Input channels: 
#>    name           train predict
#>  <char>          <char>  <char>
#>   input ModelDescriptor    Task
#> 
#> ── Output channels: 
#>    name           train predict
#>  <char>          <char>  <char>
#>  output ModelDescriptor    Task
# The available parameters
pipeop$param_set
#> <ParamSet(2)>
#>         id    class lower upper nlevels default  value
#>     <char>   <char> <num> <num>   <num>  <list> <list>
#> 1:       p ParamDbl     0     1     Inf     0.5 [NULL]
#> 2: inplace ParamLgl    NA    NA       2   FALSE [NULL]