ONE - On-device Neural Engine
Loading...
Searching...
No Matches
Public Member Functions
loco::FilterEncoder Struct Referenceabstract

Decribe how to build a (convolution) filter from a tensor. More...

#include <FilterCodec.h>

Public Member Functions

virtual ~FilterEncoder ()=default
 
virtual FilterShape shape (const TensorShape &shape) const =0
 
virtual TensorIndex value (const FilterIndex &index) const =0
 

Detailed Description

Decribe how to build a (convolution) filter from a tensor.

Let us assume that "enc" is a filter encoder.

Given a tensor "inp" and its shape "inp.shape", "enc" builds a filter "out" as follows:

for each valid filter index (referred to as filter_index below) for enc.shape(inp.shape) out.at(filter_index) = inp.at(enc.value(filter_index))

Definition at line 42 of file FilterCodec.h.

Constructor & Destructor Documentation

◆ ~FilterEncoder()

virtual loco::FilterEncoder::~FilterEncoder ( )
virtualdefault

Member Function Documentation

◆ shape()

virtual FilterShape loco::FilterEncoder::shape ( const TensorShape &  shape) const
pure virtual

Implemented in loco::PermutingEncoder< Domain::Filter >.

Referenced by RandomDataGenerator.RandomDataGenerator::_gen_float32(), RandomDataGenerator.RandomDataGenerator::_gen_int16(), and RandomDataGenerator.RandomDataGenerator::_gen_uint8().

◆ value()

virtual TensorIndex loco::FilterEncoder::value ( const FilterIndex &  index) const
pure virtual

Implemented in loco::PermutingEncoder< Domain::Filter >.

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