Depthwise separable 1D convolution.

Inherits From: Layer, Module

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.

filters Integer, the dimensionality of the output space (i.e. the number of filte