ยป Keras API reference / Layers API / Convolution layers / SeparableConv1D layer

SeparableConv1D layer

SeparableConv1D class

tf.keras.layers.SeparableConv1D(
    filters,
    kernel_size,
    strides=1,
    padding="valid",
    data_format=None,
    dilation_rate=1,
    depth_multiplier=1,
    activation=None,
    use_bias=True,
    depthwise_initializer="glorot_uniform",
    pointwise_initializer="glorot_uniform",
    bias_initializer="zeros",
    depthwise_regularizer=None,
    pointwise_regularizer=None,
    bias_regularizer=None,
    activity_regularizer=None,
    depthwise_constraint=None,
    pointwise_constraint=None,
    bias_constraint=None,
    **kwargs
)

Depthwise separable 1D convolution.

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.

Arguments

  • filters: Integer, the dimensionality of the output space (i.e. the number of filters in the convolution).
  • kernel_size: A single integer specifying the spatial dimensions of the filters.
  • strides: A single integer specifying the strides of the convolution. Specifying any stride value != 1 is incompatible with specifying any dilation_rate value != 1.
  • padding: One of "valid", "same", or "causal" (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. "causal" results in causal (dilated) convolutions, e.g. output[t] does not depend on input[t+1:].
  • data_format: 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_size, length, channels) while channels_first corresponds to inputs with shape (batch_size, channels, length).
  • dilation_rate: A single integer, specifying the dilation rate to use for dilated convolution. Currently, specifying any dilation_rate value != 1 is incompatible with specifying any stride value != 1.
  • 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 num_filters_in * depth_multiplier.
  • activation: Activation function to use. If you don't specify anything, no activation is applied ( see keras.activations).
  • use_bias: Boolean, whether the layer uses a bias.
  • depthwise_initializer: An initializer for the depthwise convolution kernel ( see keras.initializers).
  • pointwise_initializer: An initializer for the pointwise convolution kernel ( see keras.initializers).
  • bias_initializer: An initializer for the bias vector. If None, the default initializer will be used (see keras.initializers).
  • depthwise_regularizer: Optional regularizer for the depthwise convolution kernel (see keras.regularizers).
  • pointwise_regularizer: Optional regularizer for the pointwise convolution kernel (see keras.regularizers).
  • bias_regularizer: Optional regularizer for the bias vector ( see keras.regularizers).
  • activity_regularizer: Optional regularizer function for the output ( see keras.regularizers).
  • 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). Constraints are not safe to use when doing asynchronous distributed training ( see keras.constraints).
  • pointwise_constraint: Optional projection function to be applied to the pointwise kernel after being updated by an Optimizer ( see keras.constraints).
  • bias_constraint: Optional projection function to be applied to the bias after being updated by an Optimizer ( see keras.constraints).
  • trainable: Boolean, if True the weights of this layer will be marked as trainable (and listed in layer.trainable_weights).
  • name: A string, the name of the layer.

Input shape

3D tensor with shape: (batch_size, channels, steps) if data_format='channels_first' or 5D tensor with shape: (batch_size, steps, channels) if data_format='channels_last'.

Output shape

3D tensor with shape: (batch_size, filters, new_steps) if data_format='channels_first' or 3D tensor with shape: (batch_size, new_steps, filters) if data_format='channels_last'. new_steps value might have changed due to padding or strides.

Returns

A tensor of rank 3 representing activation(separableconv1d(inputs, kernel) + bias).

Raises

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