Skip to contents

This layer performs a depthwise convolution that acts separately on channels, followed by a pointwise convolution that mixes channels. If use_bias is TRUE and a bias initializer is provided, it adds a bias vector to the output. It then optionally applies an activation function to produce the final output.

Usage

layer_separable_conv_2d(
  object,
  filters,
  kernel_size,
  strides = list(1L, 1L),
  padding = "valid",
  data_format = NULL,
  dilation_rate = list(1L, 1L),
  depth_multiplier = 1L,
  activation = NULL,
  use_bias = TRUE,
  depthwise_initializer = "glorot_uniform",
  pointwise_initializer = "glorot_uniform",
  bias_initializer = "zeros",
  depthwise_regularizer = NULL,
  pointwise_regularizer = NULL,
  bias_regularizer = NULL,
  activity_regularizer = NULL,
  depthwise_constraint = NULL,
  pointwise_constraint = NULL,
  bias_constraint = NULL,
  ...
)

Arguments

object

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

filters

int, the dimensionality of the output space (i.e. the number of filters in the pointwise convolution).

kernel_size

int or list of 2 integers, specifying the size of the depthwise convolution window.

strides

int or list of 2 integers, specifying the stride length of the depthwise convolution. If only one int is specified, the same stride size will be used for all dimensions. strides > 1 is incompatible with dilation_rate > 1.

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. When padding="same" and strides=1, the output has the same size 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".

dilation_rate

int or list of 2 integers, specifying the dilation rate to use for dilated convolution. If only one int is specified, the same dilation rate will be used for all dimensions.

depth_multiplier

The number of depthwise convolution output channels for each input channel. The total number of depthwise convolution output channels will be equal to input_channel * depth_multiplier.

activation

Activation function. If NULL, no activation is applied.

use_bias

bool, if TRUE, bias will be added to the output.

depthwise_initializer

An initializer for the depthwise convolution kernel. If NULL, then the default initializer ("glorot_uniform") will be used.

pointwise_initializer

An initializer for the pointwise convolution kernel. If NULL, then the default initializer ("glorot_uniform") will be used.

bias_initializer

An initializer for the bias vector. If NULL, the default initializer ('"zeros"') will be used.

depthwise_regularizer

Optional regularizer for the depthwise convolution kernel.

pointwise_regularizer

Optional regularizer for the pointwise convolution kernel.

bias_regularizer

Optional regularizer for the bias vector.

activity_regularizer

Optional regularizer function for the output.

depthwise_constraint

Optional projection function to be applied to the depthwise kernel after being updated by an Optimizer (e.g. used for norm constraints or value constraints for layer weights). The function must take as input the unprojected variable and must return the projected variable (which must have the same shape).

pointwise_constraint

Optional projection function to be applied to the pointwise kernel after being updated by an Optimizer.

bias_constraint

Optional projection function to be applied to the bias after being updated by an Optimizer.

...

For forward/backward compatability.

Value

A 4D tensor representing activation(separable_conv2d(inputs, kernel) + bias).

Input Shape

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

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

Output Shape

  • If data_format="channels_last": A 4D tensor with shape: (batch_size, new_height, new_width, filters)

  • If data_format="channels_first": A 4D tensor with shape: (batch_size, filters, new_height, new_width)

Example

x <- random_uniform(c(4, 10, 10, 12))
y <- layer_separable_conv_2d(x, 3, c(4, 3), 2, activation='relu')
shape(y)

## shape(4, 4, 4, 3)

See also

Other convolutional layers:
layer_conv_1d()
layer_conv_1d_transpose()
layer_conv_2d()
layer_conv_2d_transpose()
layer_conv_3d()
layer_conv_3d_transpose()
layer_depthwise_conv_1d()
layer_depthwise_conv_2d()
layer_separable_conv_1d()

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_2d()
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_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()