Skip to contents

Linear Layer

Source: R/PipeOpTorchLinear.R
mlr_pipeops_nn_linear.Rd

Applies a linear transformation to the incoming data: \(y = xA^T + b\).

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().

Credit

Part of this documentation have been copied or adapted from the documentation of torch.

Parameters

  • out_features :: integer(1)
    The output features of the linear layer.

  • bias :: logical(1)
    Whether to use a bias. Default is TRUE.

Internals

Calls torch::nn_linear() when trained where the parameter in_features is inferred as the second to last dimension of the input tensor.

See also

Other PipeOps: mlr_pipeops_nn_avg_pool1d, mlr_pipeops_nn_avg_pool2d, mlr_pipeops_nn_avg_pool3d, mlr_pipeops_nn_batch_norm1d, mlr_pipeops_nn_batch_norm2d, mlr_pipeops_nn_batch_norm3d, mlr_pipeops_nn_block, mlr_pipeops_nn_celu, mlr_pipeops_nn_conv1d, mlr_pipeops_nn_conv2d, mlr_pipeops_nn_conv3d, mlr_pipeops_nn_conv_transpose1d, mlr_pipeops_nn_conv_transpose2d, mlr_pipeops_nn_conv_transpose3d, mlr_pipeops_nn_dropout, mlr_pipeops_nn_elu, mlr_pipeops_nn_flatten, mlr_pipeops_nn_gelu, mlr_pipeops_nn_glu, mlr_pipeops_nn_hardshrink, mlr_pipeops_nn_hardsigmoid, mlr_pipeops_nn_hardtanh, mlr_pipeops_nn_head, mlr_pipeops_nn_layer_norm, mlr_pipeops_nn_leaky_relu, mlr_pipeops_nn_log_sigmoid, mlr_pipeops_nn_max_pool1d, mlr_pipeops_nn_max_pool2d, mlr_pipeops_nn_max_pool3d, mlr_pipeops_nn_merge, mlr_pipeops_nn_merge_cat, mlr_pipeops_nn_merge_prod, mlr_pipeops_nn_merge_sum, mlr_pipeops_nn_prelu, mlr_pipeops_nn_relu, mlr_pipeops_nn_relu6, mlr_pipeops_nn_reshape, mlr_pipeops_nn_rrelu, mlr_pipeops_nn_selu, mlr_pipeops_nn_sigmoid, mlr_pipeops_nn_softmax, mlr_pipeops_nn_softplus, mlr_pipeops_nn_softshrink, mlr_pipeops_nn_softsign, mlr_pipeops_nn_squeeze, mlr_pipeops_nn_tanh, mlr_pipeops_nn_tanhshrink, mlr_pipeops_nn_threshold, mlr_pipeops_nn_unsqueeze, mlr_pipeops_torch_ingress, mlr_pipeops_torch_ingress_categ, mlr_pipeops_torch_ingress_ltnsr, mlr_pipeops_torch_ingress_num, mlr_pipeops_torch_loss, mlr_pipeops_torch_model, mlr_pipeops_torch_model_classif, mlr_pipeops_torch_model_regr

Super classes

mlr3pipelines::PipeOp -> mlr3torch::PipeOpTorch -> PipeOpTorchLinear

Methods

Public methods

Inherited methods

Method new()

Creates a new instance of this R6 class.

Usage

PipeOpTorchLinear$new(id = "nn_linear", 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.

Method clone()

The objects of this class are cloneable with this method.

Usage

PipeOpTorchLinear$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

Examples

# Construct the PipeOp
pipeop = po("nn_linear", out_features = 10)
pipeop
#> PipeOp: <nn_linear> (not trained)
#> values: <out_features=10>
#> Input channels <name [train type, predict type]>:
#>   input [ModelDescriptor,Task]
#> Output channels <name [train type, predict type]>:
#>   output [ModelDescriptor,Task]
# The available parameters
pipeop$param_set
#> <ParamSet(2)>
#>              id    class lower upper nlevels        default  value
#>          <char>   <char> <num> <num>   <num>         <list> <list>
#> 1: out_features ParamInt     1   Inf     Inf <NoDefault[0]>     10
#> 2:         bias ParamLgl    NA    NA       2           TRUE [NULL]