Skip to contents

Categorical Tokenizer

Source: R/PipeOpTorchTokenizer.R
mlr_pipeops_nn_tokenizer_categ.Rd

Tokenizes categorical features into a dense embedding. For an input of shape (batch, n_features) the output shape is (batch, n_features, d_token).

nn_module

Calls nn_tokenizer_categ() when trained where the parameter cardinalities is inferred. The output shape is (batch, n_features, d_token).

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().

Parameters

  • d_token :: integer(1)
    The dimension of the embedding.

  • bias :: logical(1)
    Whether to use a bias. Is initialized to TRUE.

  • initialization :: character(1)
    The initialization method for the embedding weights. Possible values are "uniform" (default) and "normal".

See also

Other PipeOps: mlr_pipeops_nn_adaptive_avg_pool1d, mlr_pipeops_nn_adaptive_avg_pool2d, mlr_pipeops_nn_adaptive_avg_pool3d, 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_ft_cls, mlr_pipeops_nn_geglu, 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_identity, mlr_pipeops_nn_layer_norm, mlr_pipeops_nn_leaky_relu, mlr_pipeops_nn_linear, 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_reglu, 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_tokenizer_num, 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 -> PipeOpTorchTokenizerCateg

Methods

Public methods

Inherited methods

Method new()

Creates a new instance of this R6 class.

Usage

PipeOpTorchTokenizerCateg$new(id = "nn_tokenizer_categ", 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

PipeOpTorchTokenizerCateg$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

Examples

# Construct the PipeOp
pipeop = po("nn_tokenizer_categ", d_token = 10)
pipeop
#> PipeOp: <nn_tokenizer_categ> (not trained)
#> values: <d_token=10, bias=TRUE, initialization=uniform>
#> 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(3)>
#>                id    class lower upper nlevels        default   value
#>            <char>   <char> <num> <num>   <num>         <list>  <list>
#> 1:        d_token ParamInt     1   Inf     Inf <NoDefault[0]>      10
#> 2:           bias ParamLgl    NA    NA       2 <NoDefault[0]>    TRUE
#> 3: initialization ParamFct    NA    NA       2 <NoDefault[0]> uniform