Skip to contents

Transpose 1D Convolution

Source: R/PipeOpTorchConvTranspose.R
mlr_pipeops_nn_conv_transpose1d.Rd

Applies a 1D transposed convolution operator over an input signal composed of several input planes, sometimes also called "deconvolution".

nn_module

Calls nn_conv_transpose1d. The parameter in_channels is inferred as the second dimension of the input tensor.

Parameters

  • out_channels :: integer(1)
    Number of output channels produce by the convolution.

  • kernel_size :: integer()
    Size of the convolving kernel.

  • stride :: integer()
    Stride of the convolution. Default: 1.

  • padding :: integer()\cr dilation * (kernel_size - 1) - padding` zero-padding will be added to both sides of the input. Default: 0.

  • output_padding ::integer()
    Additional size added to one side of the output shape. Default: 0.

  • groups :: integer()
    Number of blocked connections from input channels to output channels. Default: 1

  • bias :: logical(1)
    If True, adds a learnable bias to the output. Default: TRUE.

  • dilation :: integer()
    Spacing between kernel elements. Default: 1.

  • padding_mode :: character(1)
    The padding mode. One of "zeros", "reflect", "replicate", or "circular". Default is "zeros".

State

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

Input and Output Channels

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

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_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_ft_transformer_block, 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_categ, 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 -> PipeOpTorch -> PipeOpTorchConvTranspose -> PipeOpTorchConvTranspose1D

Methods

Public methods

Inherited methods

PipeOpTorchConvTranspose1D$new()

Creates a new instance of this R6 class.

Usage

PipeOpTorchConvTranspose1D$new(id = "nn_conv_transpose1d", 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.

PipeOpTorchConvTranspose1D$clone()

The objects of this class are cloneable with this method.

Usage

PipeOpTorchConvTranspose1D$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

Examples

# Construct the PipeOp
pipeop = po("nn_conv_transpose1d", kernel_size = 3, out_channels = 2)
pipeop
#> 
#> ── PipeOp <nn_conv_transpose1d>: not trained ───────────────────────────────────
#> Values: out_channels=2, kernel_size=3
#> 
#> ── Input channels: 
#>    name           train predict
#>  <char>          <char>  <char>
#>   input ModelDescriptor    Task
#> 
#> ── Output channels: 
#>    name           train predict
#>  <char>          <char>  <char>
#>  output ModelDescriptor    Task
# The available parameters
pipeop$param_set
#> <ParamSet(9)>
#>                id    class lower upper nlevels        default  value
#>            <char>   <char> <num> <num>   <num>         <list> <list>
#> 1:   out_channels ParamInt     1   Inf     Inf <NoDefault[0]>      2
#> 2:    kernel_size ParamUty    NA    NA     Inf <NoDefault[0]>      3
#> 3:         stride ParamUty    NA    NA     Inf              1 [NULL]
#> 4:        padding ParamUty    NA    NA     Inf              0 [NULL]
#> 5: output_padding ParamUty    NA    NA     Inf              0 [NULL]
#> 6:       dilation ParamUty    NA    NA     Inf              1 [NULL]
#> 7:         groups ParamInt     1   Inf     Inf              1 [NULL]
#> 8:           bias ParamLgl    NA    NA       2           TRUE [NULL]
#> 9:   padding_mode ParamFct    NA    NA       4          zeros [NULL]