Torch Entry Point for Numeric Features

Ingress PipeOp that represents a numeric (integer() and numeric()) entry point to a torch network.

Internals

Uses batchgetter_num().

Input and Output Channels

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

State

The state is set to the input shape.

See also

Other Graph Network: ModelDescriptor(), TorchIngressToken(), mlr_learners_torch_model, mlr_pipeops_module, mlr_pipeops_torch, mlr_pipeops_torch_ingress, mlr_pipeops_torch_ingress_categ, mlr_pipeops_torch_ingress_ltnsr, model_descriptor_to_learner(), model_descriptor_to_module(), model_descriptor_union(), nn_graph()

Super classes

mlr3pipelines::PipeOp -> PipeOpTorchIngress -> PipeOpTorchIngressNumeric

Methods

Public methods

• PipeOpTorchIngressNumeric$new()

• PipeOpTorchIngressNumeric$clone()

Inherited methods

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

---

PipeOpTorchIngressNumeric$new()

Creates a new instance of this R6 class.

Usage

PipeOpTorchIngressNumeric$new(id = "torch_ingress_num", 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.

---

PipeOpTorchIngressNumeric$clone()

The objects of this class are cloneable with this method.

Usage

PipeOpTorchIngressNumeric$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

Examples

graph = po("select", selector = selector_type(c("numeric", "integer"))) %>>%
  po("torch_ingress_num")
task = tsk("german_credit")
# The output is a model descriptor
md = graph$train(task)[[1L]]
ingress = md$ingress[[1L]]
ingress$batchgetter(task$data(1:5, ingress$features(task)), "cpu")
#> torch_tensor
#>    67  1169     6
#>    22  5951    48
#>    49  2096    12
#>    45  7882    42
#>    53  4870    24
#> [ CPUFloatType{5,3} ]