Separable convolutions consist in first performing a depthwise spatial convolution (which acts on each input channel separately) followed by a pointwise convolution which mixes together the resulting output channels. The depth_multiplier argument controls how many output channels are generated per input channel in the depthwise step. Intuitively, separable convolutions can be understood as a way to factorize a convolution kernel into two smaller kernels, or as an extreme version of an Inception block.

layer_separable_conv_2d(
object,
filters,
kernel_size,
strides = c(1, 1),
data_format = NULL,
dilation_rate = 1,
depth_multiplier = 1,
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,
input_shape = NULL,
batch_input_shape = NULL,
batch_size = NULL,
dtype = NULL,
name = NULL,
trainable = NULL,
weights = NULL
)

## Arguments

object Model or layer object Integer, the dimensionality of the output space (i.e. the number of output filters in the convolution). An integer or list of 2 integers, specifying the width and height of the 2D convolution window. Can be a single integer to specify the same value for all spatial dimensions. An integer or list of 2 integers, specifying the strides of the convolution along the width and height. Can be a single integer to specify the same value for all spatial dimensions. Specifying any stride value != 1 is incompatible with specifying any dilation_rate value != 1. one of "valid" or "same" (case-insensitive). A string, one of channels_last (default) 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". an integer or list of 2 integers, specifying the dilation rate to use for dilated convolution. Can be a single integer to specify the same value for all spatial dimensions. Currently, specifying any dilation_rate value != 1 is incompatible with specifying any stride value != 1. The number of depthwise convolution output channels for each input channel. The total number of depthwise convolution output channels will be equal to filters_in * depth_multiplier. Activation function to use. If you don't specify anything, no activation is applied (ie. "linear" activation: a(x) = x). Boolean, whether the layer uses a bias vector. Initializer for the depthwise kernel matrix. Initializer for the pointwise kernel matrix. Initializer for the bias vector. Regularizer function applied to the depthwise kernel matrix. Regularizer function applied to the pointwise kernel matrix. Regularizer function applied to the bias vector. Regularizer function applied to the output of the layer (its "activation").. Constraint function applied to the depthwise kernel matrix. Constraint function applied to the pointwise kernel matrix. Constraint function applied to the bias vector. Dimensionality of the input (integer) not including the samples axis. This argument is required when using this layer as the first layer in a model. Shapes, including the batch size. For instance, batch_input_shape=c(10, 32) indicates that the expected input will be batches of 10 32-dimensional vectors. batch_input_shape=list(NULL, 32) indicates batches of an arbitrary number of 32-dimensional vectors. Fixed batch size for layer The data type expected by the input, as a string (float32, float64, int32...) An optional name string for the layer. Should be unique in a model (do not reuse the same name twice). It will be autogenerated if it isn't provided. Whether the layer weights will be updated during training. Initial weights for layer.

## Input shape

4D tensor with shape: (batch, channels, rows, cols) if data_format='channels_first' or 4D tensor with shape: (batch, rows, cols, channels) if data_format='channels_last'.

## Output shape

4D tensor with shape: (batch, filters, new_rows, new_cols) if data_format='channels_first' or 4D tensor with shape: (batch, new_rows, new_cols, filters) if data_format='channels_last'. rows and cols values might have changed due to padding.

Other convolutional layers: layer_conv_1d_transpose(), layer_conv_1d(), layer_conv_2d_transpose(), layer_conv_2d(), layer_conv_3d_transpose(), layer_conv_3d(), layer_conv_lstm_2d(), layer_cropping_1d(), layer_cropping_2d(), layer_cropping_3d(), layer_depthwise_conv_2d(), layer_separable_conv_1d(), layer_upsampling_1d(), layer_upsampling_2d(), layer_upsampling_3d(), layer_zero_padding_1d(), layer_zero_padding_2d(), layer_zero_padding_3d()