Recurrent Layer

Base class for the recurrent layers PipeOpTorchRNN, PipeOpTorchLSTM and PipeOpTorchGRU.

Parameters

See the respective child class.

State

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

Input and Output Channels

One input channel "input", and the output channels described in the child classes. For an explanation see PipeOpTorch.

See also

Other PipeOps: mlr_pipeops_torch_model

Super classes

mlr3pipelines::PipeOp -> PipeOpTorch -> PipeOpTorchRecurrent

Methods

Public methods

• PipeOpTorchRecurrent$new()

• PipeOpTorchRecurrent$clone()

Inherited methods

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

---

PipeOpTorchRecurrent$new()

Creates a new instance of this R6 class.

Usage

PipeOpTorchRecurrent$new(id, type, param_set, param_vals = list())

Arguments

id

(character(1))
Identifier of the resulting object.

type

(character(1))
Which recurrent layer to build, one of "rnn", "lstm" or "gru".

param_set

(ParamSet)
The parameter set.

param_vals

(list())
List of hyperparameter settings, overwriting the hyperparameter settings that would otherwise be set during construction.

---

PipeOpTorchRecurrent$clone()

The objects of this class are cloneable with this method.

Usage

PipeOpTorchRecurrent$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.