2D Max Pooling

Applies a 2D max pooling over an input signal composed of several input planes.

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.

Internals

Calls torch::nn_max_pool2d() during training.

Input and Output Channels

If return_indices is FALSE during construction, there is one input channel 'input' and one output channel 'output'. If return_indices is TRUE, there are two output channels 'output' and 'indices'. For an explanation see PipeOpTorch.

Parameters

• kernel_size :: integer()
  The size of the window. Can be single number or a vector.

• stride :: (integer(1))
  The stride of the window. Can be a single number or a vector. Default: kernel_size

• padding :: integer()
  Implicit zero paddings on both sides of the input. Can be a single number or a tuple (padW,). Default: 0

• dilation :: integer()
  Controls the spacing between the kernel points; also known as the à trous algorithm. Default: 1

• ceil_mode :: logical(1)
  When True, will use ceil instead of floor to compute the output shape. Default: FALSE

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_linear, mlr_pipeops_nn_log_sigmoid, mlr_pipeops_nn_max_pool1d, 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 -> mlr3torch::PipeOpTorchMaxPool -> PipeOpTorchMaxPool2D

Methods

Public methods

• PipeOpTorchMaxPool2D$new()

• PipeOpTorchMaxPool2D$clone()

Inherited methods

• mlr3pipelines::PipeOp$help()
• mlr3pipelines::PipeOp$predict()
• mlr3pipelines::PipeOp$print()
• mlr3pipelines::PipeOp$train()
• mlr3torch::PipeOpTorch$shapes_out()

---

Method new()

Creates a new instance of this R6 class.

Usage

PipeOpTorchMaxPool2D$new(
  id = "nn_max_pool2d",
  return_indices = FALSE,
  param_vals = list()
)

Arguments

id

(character(1))
Identifier of the resulting object.

return_indices

(logical(1))
Whether to return the indices. If this is TRUE, there are two output channels "output" and "indices".

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

PipeOpTorchMaxPool2D$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

Examples

# Construct the PipeOp
pipeop = po("nn_max_pool2d")
pipeop
#> PipeOp: <nn_max_pool2d> (not trained)
#> values: <list()>
#> 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(5)>
#>             id    class lower upper nlevels        default  value
#>         <char>   <char> <num> <num>   <num>         <list> <list>
#> 1: kernel_size ParamUty    NA    NA     Inf <NoDefault[0]> [NULL]
#> 2:     padding ParamUty    NA    NA     Inf              0 [NULL]
#> 3:      stride ParamUty    NA    NA     Inf         [NULL] [NULL]
#> 4:    dilation ParamInt  -Inf   Inf     Inf              1 [NULL]
#> 5:   ceil_mode ParamLgl    NA    NA       2          FALSE [NULL]