Skip to contents

Depthwise convolution is a type of convolution in which each input channel is convolved with a different kernel (called a depthwise kernel). You can understand depthwise convolution as the first step in a depthwise separable convolution.

It is implemented via the following steps:

  • Split the input into individual channels.

  • Convolve each channel with an individual depthwise kernel with depth_multiplier output channels.

  • Concatenate the convolved outputs along the channels axis.

Unlike a regular 1D convolution, depthwise convolution does not mix information across different input channels.

The depth_multiplier argument determines how many filters are applied to one input channel. As such, it controls the amount of output channels that are generated per input channel in the depthwise step.

Usage

layer_depthwise_conv_1d(
  object,
  kernel_size,
  strides = 1L,
  padding = "valid",
  depth_multiplier = 1L,
  data_format = NULL,
  dilation_rate = 1L,
  activation = NULL,
  use_bias = TRUE,
  depthwise_initializer = "glorot_uniform",
  bias_initializer = "zeros",
  depthwise_regularizer = NULL,
  bias_regularizer = NULL,
  activity_regularizer = NULL,
  depthwise_constraint = NULL,
  bias_constraint = NULL,
  ...
)

Arguments

object

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

kernel_size

int or list of 1 integer, specifying the size of the depthwise convolution window.

strides

int or list of 1 integer, specifying the stride length of the convolution. 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.

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.

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, steps, features) while "channels_first" corresponds to inputs with shape (batch, features, steps). 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 1 integers, specifying the dilation rate to use for dilated convolution.

activation

Activation function. If NULL, no activation is applied.

use_bias

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

depthwise_initializer

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

bias_initializer

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

depthwise_regularizer

Optional regularizer for the 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 kernel after being updated by an Optimizer (e.g. used to implement 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). Constraints are not safe to use when doing asynchronous distributed training.

bias_constraint

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

...

For forward/backward compatability.

Value

A 3D tensor representing activation(depthwise_conv1d(inputs, kernel) + bias).

Input Shape

  • If data_format="channels_last": A 3D tensor with shape: (batch_shape, steps, channels)

  • If data_format="channels_first": A 3D tensor with shape: (batch_shape, channels, steps)

Output Shape

  • If data_format="channels_last": A 3D tensor with shape: (batch_shape, new_steps, channels * depth_multiplier)

  • If data_format="channels_first": A 3D tensor with shape: (batch_shape, channels * depth_multiplier, new_steps)

Raises

ValueError: when both strides > 1 and dilation_rate > 1.

Examples

x <- random_uniform(c(4, 10, 12))
y <- x |> layer_depthwise_conv_1d(
  kernel_size = 3,
  depth_multiplier = 3,
  activation = 'relu'
)
shape(y)

## shape(4, 8, 36)

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_2d()
layer_separable_conv_1d()
layer_separable_conv_2d()

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_2d()
layer_discretization()
layer_dot()
layer_dropout()
layer_einsum_dense()
layer_embedding()
layer_feature_space()
layer_flatten()
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_lambda()
layer_layer_normalization()
layer_lstm()
layer_masking()
layer_max_pooling_1d()
layer_max_pooling_2d()
layer_max_pooling_3d()
layer_maximum()
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()