Thresholds each element of the input Tensor.
nn_module
Calls torch::nn_threshold() when trained.
Parameters
threshold::numeric(1)
The value to threshold at.value::numeric(1)
The value to replace with.inplace::logical(1)
Can optionally do the 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.
Super classes
mlr3pipelines::PipeOp -> PipeOpTorch -> PipeOpTorchThreshold
Methods
PipeOpTorchThreshold$new()
Creates a new instance of this R6 class.
Usage
PipeOpTorchThreshold$new(id = "nn_threshold", 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.
Examples
# Construct the PipeOp
pipeop = nn("threshold", threshold = 1, value = 2)
pipeop
#>
#> ── PipeOp <threshold>: not trained ─────────────────────────────────────────────
#> Values: threshold=1, value=2
#>
#> ── 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: threshold ParamDbl -Inf Inf Inf <NoDefault[0]> 1
#> 2: value ParamDbl -Inf Inf Inf <NoDefault[0]> 2
#> 3: inplace ParamLgl NA NA 2 FALSE [NULL]