2D Average Pooling

Applies 2D average-pooling operation in \(kH * kW\) regions by step size \(sH * sW\) steps. The number of output features is equal to the number of input planes.

nn_module

Calls nn_avg_pool2d() during training.

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

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

• stride :: integer()
  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 vector. Default: 0.

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

• count_include_pad :: logical(1)
  When TRUE, will include the zero-padding in the averaging calculation. Default: TRUE.

• divisor_override :: logical(1)
  If specified, it will be used as divisor, otherwise size of the pooling region will be used. Default: NULL. Only available for dimension greater than 1.

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_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_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 -> mlr3torch::PipeOpTorch -> mlr3torch::PipeOpTorchAvgPool -> PipeOpTorchAvgPool2D

Methods

Public methods

• PipeOpTorchAvgPool2D$new()

• PipeOpTorchAvgPool2D$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

PipeOpTorchAvgPool2D$new(id = "nn_avg_pool2d", 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

PipeOpTorchAvgPool2D$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

Examples

# Construct the PipeOp
pipeop = po("nn_avg_pool2d")
pipeop
#> PipeOp: <nn_avg_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(6)>
#>                   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:            stride ParamUty    NA    NA     Inf         [NULL] [NULL]
#> 3:           padding ParamUty    NA    NA     Inf              0 [NULL]
#> 4:         ceil_mode ParamLgl    NA    NA       2          FALSE [NULL]
#> 5: count_include_pad ParamLgl    NA    NA       2           TRUE [NULL]
#> 6:  divisor_override ParamDbl     0   Inf     Inf         [NULL] [NULL]