Skip to contents

Hard Tanh Activation Function

Source: R/PipeOpTorchActivation.R
mlr_pipeops_nn_hardtanh.Rd

Applies the HardTanh function element-wise.

nn_module

Calls torch::nn_hardtanh() when trained.

Parameters

  • min_val :: numeric(1)
    Minimum value of the linear region range. Default: -1.

  • max_val :: numeric(1)
    Maximum value of the linear region range. Default: 1.

  • inplace :: logical(1)
    Can optionally do the operation in-place. Default: FALSE.

State

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

Super classes

mlr3pipelines::PipeOp -> PipeOpTorch -> PipeOpTorchHardTanh

Methods

Public methods

Inherited methods

PipeOpTorchHardTanh$new()

Creates a new instance of this R6 class.

Usage

PipeOpTorchHardTanh$new(id = "nn_hardtanh", 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.

PipeOpTorchHardTanh$clone()

The objects of this class are cloneable with this method.

Usage

PipeOpTorchHardTanh$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

Examples

# Construct the PipeOp
pipeop = nn("hardtanh")
pipeop
#> 
#> ── PipeOp <hardtanh>: 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(3)>
#>         id    class lower upper nlevels default  value
#>     <char>   <char> <num> <num>   <num>  <list> <list>
#> 1: min_val ParamDbl  -Inf   Inf     Inf      -1 [NULL]
#> 2: max_val ParamDbl  -Inf   Inf     Inf       1 [NULL]
#> 3: inplace ParamLgl    NA    NA       2   FALSE [NULL]