model_descriptor_to_module: Create a nn_graph from ModelDescriptor

In mlr3torch: Deep Learning with 'mlr3'

Create a nn_graph from ModelDescriptor

Description

Creates the nn_graph from a ModelDescriptor. Mostly for internal use, since the ModelDescriptor is in most circumstances harder to use than just creating nn_graph directly.

Usage

model_descriptor_to_module(
  model_descriptor,
  output_pointers = NULL,
  list_output = FALSE
)

Arguments

model_descriptor	(ModelDescriptor) Model Descriptor. pointer is ignored, instead output_pointer values are used. ⁠$graph⁠ member is modified by-reference.
output_pointers	(list of character) Collection of pointers that indicate what part of the model_descriptor$graph is being used for output. Entries have the format of ModelDescriptor$pointer.
list_output	(logical(1)) Whether output should be a list of tensors. If FALSE, then length(output_pointers) must be 1.

Value

nn_graph

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, mlr_pipeops_torch_ingress_num, model_descriptor_to_learner(), model_descriptor_union(), nn_graph()

mlr3torch documentation built on April 4, 2025, 3:03 a.m.