Skip to contents

Max pooling operation for 2D spatial data.

Source: R/layers-pooling.R
layer_max_pooling_2d.Rd

Downsamples the input along its spatial dimensions (height and width) by taking the maximum value over an input window (of size defined by pool_size) for each channel of the input. The window is shifted by strides along each dimension.

The resulting output when using the "valid" padding option has a spatial shape (number of rows or columns) of: output_shape = floor((input_shape - pool_size) / strides) + 1 (when input_shape >= pool_size)

The resulting output shape when using the "same" padding option is: output_shape = floor((input_shape - 1) / strides) + 1

Usage

layer_max_pooling_2d(
  object,
  pool_size = list(2L, 2L),
  strides = NULL,
  padding = "valid",
  data_format = NULL,
  name = NULL,
  ...
)

Arguments

object

Object to compose the layer with. A tensor, array, or sequential model.

pool_size

int or list of 2 integers, factors by which to downscale (dim1, dim2). If only one integer is specified, the same window length will be used for all dimensions.

strides

int or list of 2 integers, or NULL. Strides values. If NULL, it will default to pool_size. If only one int is specified, the same stride size will be used for all dimensions.

padding

string, either "valid" or "same" (case-insensitive). "valid" means no padding. "same" results in padding evenly to the left/right or up/down of the input such that output has the same height/width dimension as the input.

data_format

string, either "channels_last" or "channels_first". The ordering of the dimensions in the inputs. "channels_last" corresponds to inputs with shape (batch, height, width, channels) while "channels_first" corresponds to inputs with shape (batch, channels, height, width). It defaults to the image_data_format value found in your Keras config file at ~/.keras/keras.json. If you never set it, then it will be "channels_last".

name

String, name for the object

...

For forward/backward compatability.

Value

The return value depends on the value provided for the first argument. If object is:

  • a keras_model_sequential(), then the layer is added to the sequential model (which is modified in place). To enable piping, the sequential model is also returned, invisibly.

  • a keras_input(), then the output tensor from calling layer(input) is returned.

  • NULL or missing, then a Layer instance is returned.

Input Shape

  • If data_format="channels_last": 4D tensor with shape (batch_size, height, width, channels).

  • If data_format="channels_first": 4D tensor with shape (batch_size, channels, height, width).

Output Shape

  • If data_format="channels_last": 4D tensor with shape (batch_size, pooled_height, pooled_width, channels).

  • If data_format="channels_first": 4D tensor with shape (batch_size, channels, pooled_height, pooled_width).

Examples

strides = (1, 1) and padding = "valid":

x <- rbind(c(1., 2., 3.),
           c(4., 5., 6.),
           c(7., 8., 9.)) |> op_reshape(c(1, 3, 3, 1))
max_pool_2d <- layer_max_pooling_2d(pool_size = c(2, 2),
                                    strides = c(1, 1),
                                    padding = "valid")
max_pool_2d(x)

## tf.Tensor(
## [[[[5.]
##    [6.]]
##
##   [[8.]
##    [9.]]]], shape=(1, 2, 2, 1), dtype=float32)

strides = c(2, 2) and padding = "valid":

x <- rbind(c(1., 2., 3., 4.),
           c(5., 6., 7., 8.),
           c(9., 10., 11., 12.)) |> op_reshape(c(1, 3, 4, 1))
max_pool_2d <- layer_max_pooling_2d(pool_size = c(2, 2),
                                    strides = c(2, 2),
                                    padding = "valid")
max_pool_2d(x)

## tf.Tensor(
## [[[[6.]
##    [8.]]]], shape=(1, 1, 2, 1), dtype=float32)

stride = (1, 1) and padding = "same":

x <- rbind(c(1., 2., 3.),
           c(4., 5., 6.),
           c(7., 8., 9.)) |> op_reshape(c(1, 3, 3, 1))
max_pool_2d <- layer_max_pooling_2d(pool_size = c(2, 2),
                                    strides = c(1, 1),
                                    padding = "same")
max_pool_2d(x)

## tf.Tensor(
## [[[[5.]
##    [6.]
##    [6.]]
##
##   [[8.]
##    [9.]
##    [9.]]
##
##   [[8.]
##    [9.]
##    [9.]]]], shape=(1, 3, 3, 1), dtype=float32)

See also

Other pooling layers:
layer_average_pooling_1d()
layer_average_pooling_2d()
layer_average_pooling_3d()
layer_global_average_pooling_1d()
layer_global_average_pooling_2d()
layer_global_average_pooling_3d()
layer_global_max_pooling_1d()
layer_global_max_pooling_2d()
layer_global_max_pooling_3d()
layer_max_pooling_1d()
layer_max_pooling_3d()

Other layers:
Layer()
layer_activation()
layer_activation_elu()
layer_activation_leaky_relu()
layer_activation_parametric_relu()
layer_activation_relu()
layer_activation_softmax()
layer_activity_regularization()
layer_add()
layer_additive_attention()
layer_alpha_dropout()
layer_attention()
layer_average()
layer_average_pooling_1d()
layer_average_pooling_2d()
layer_average_pooling_3d()
layer_batch_normalization()
layer_bidirectional()
layer_category_encoding()
layer_center_crop()
layer_concatenate()
layer_conv_1d()
layer_conv_1d_transpose()
layer_conv_2d()
layer_conv_2d_transpose()
layer_conv_3d()
layer_conv_3d_transpose()
layer_conv_lstm_1d()
layer_conv_lstm_2d()
layer_conv_lstm_3d()
layer_cropping_1d()
layer_cropping_2d()
layer_cropping_3d()
layer_dense()
layer_depthwise_conv_1d()
layer_depthwise_conv_2d()
layer_discretization()
layer_dot()
layer_dropout()
layer_einsum_dense()
layer_embedding()
layer_feature_space()
layer_flatten()
layer_flax_module_wrapper()
layer_gaussian_dropout()
layer_gaussian_noise()
layer_global_average_pooling_1d()
layer_global_average_pooling_2d()
layer_global_average_pooling_3d()
layer_global_max_pooling_1d()
layer_global_max_pooling_2d()
layer_global_max_pooling_3d()
layer_group_normalization()
layer_group_query_attention()
layer_gru()
layer_hashed_crossing()
layer_hashing()
layer_identity()
layer_integer_lookup()
layer_jax_model_wrapper()
layer_lambda()
layer_layer_normalization()
layer_lstm()
layer_masking()
layer_max_pooling_1d()
layer_max_pooling_3d()
layer_maximum()
layer_mel_spectrogram()
layer_minimum()
layer_multi_head_attention()
layer_multiply()
layer_normalization()
layer_permute()
layer_random_brightness()
layer_random_contrast()
layer_random_crop()
layer_random_flip()
layer_random_rotation()
layer_random_translation()
layer_random_zoom()
layer_repeat_vector()
layer_rescaling()
layer_reshape()
layer_resizing()
layer_rnn()
layer_separable_conv_1d()
layer_separable_conv_2d()
layer_simple_rnn()
layer_spatial_dropout_1d()
layer_spatial_dropout_2d()
layer_spatial_dropout_3d()
layer_spectral_normalization()
layer_string_lookup()
layer_subtract()
layer_text_vectorization()
layer_tfsm()
layer_time_distributed()
layer_torch_module_wrapper()
layer_unit_normalization()
layer_upsampling_1d()
layer_upsampling_2d()
layer_upsampling_3d()
layer_zero_padding_1d()
layer_zero_padding_2d()
layer_zero_padding_3d()
rnn_cell_gru()
rnn_cell_lstm()
rnn_cell_simple()
rnn_cells_stack()