Hard Shrink Activation Function

Applies the hard shrinkage function element-wise

nn_module

Calls torch::nn_hardshrink() when trained.

Parameters

• lambd :: numeric(1)
  The lambda value for the Hardshrink formulation. Default 0.5.

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 -> PipeOpTorchHardShrink

Methods

Public methods

• PipeOpTorchHardShrink$new()

• PipeOpTorchHardShrink$clone()

Inherited methods

• mlr3pipelines::PipeOp$help()
• mlr3pipelines::PipeOp$predict()
• mlr3pipelines::PipeOp$print()
• mlr3pipelines::PipeOp$train()
• PipeOpTorch$shapes_out()

---

PipeOpTorchHardShrink$new()

Creates a new instance of this R6 class.

Usage

PipeOpTorchHardShrink$new(id = "nn_hardshrink", 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.

---

PipeOpTorchHardShrink$clone()

The objects of this class are cloneable with this method.

Usage

PipeOpTorchHardShrink$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

Examples

# Construct the PipeOp
pipeop = nn("hardshrink")
pipeop
#> 
#> ── PipeOp <hardshrink>: 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(1)>
#>        id    class lower upper nlevels default  value
#>    <char>   <char> <num> <num>   <num>  <list> <list>
#> 1:  lambd ParamDbl  -Inf   Inf     Inf     0.5 [NULL]