MayaFlux 1.0.0
Digital-First Multimedia Processing Framework
Loading...
Searching...
No Matches
MayaFlux::Yantra::TensorKernels::Conv1d Struct Reference

One convolution layer over [batch, c_in, t_in], with weights [c_out, c_in, kernel]. More...

#include <Layers.hpp>

Collaboration diagram for MayaFlux::Yantra::TensorKernels::Conv1d:

Public Attributes

Activation activation { Activation::None }
uint32_t c_in {}
uint32_t c_out {}
uint32_t dilation { 1 }
uint32_t kernel {}
uint32_t pad { 0 }
bool relu_input { false }
uint32_t stride { 1 }

Detailed Description

One convolution layer over [batch, c_in, t_in], with weights [c_out, c_in, kernel].

The input is zero padded by pad on both sides, tap k reads dilation * k samples past the window start, and windows advance by stride. relu_input applies ReLU to the input before the weights.

Definition at line 31 of file Layers.hpp.


The documentation for this struct was generated from the following file: