Patent · US Active

Method, electronic device and storage medium for convolution calculation in neural network

US12174908B2 · kind B2 · utility

0Cited by
1References
14Claims
0Family size

Assignee

Inventors

Key dates

Filing dateDec 17, 2018
Grant dateDec 24, 2024
Priority date
Expiry dateJan 11, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/045
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Disclosed is a method for convolution calculation in a neural network, comprising: reading an input feature map, depthwise convolution kernels and pointwise convolution kernels from a dynamic random access memory (DRAM); performing depthwise convolution calculations and pointwise convolution calculations by depthwise convolution calculation units and pointwise convolution calculation units, according to the input feature map, the depthwise convolution kernels and the pointwise convolution kernels to obtain output feature values of a first predetermined number p of points on all pointwise convolution output channels; storing the output feature values of a first predetermined number p of points on all pointwise convolution output channels into an on-chip memory; and repeating above operation to obtain output feature values of all points on all point wise convolution output channels. Therefore, the storage space for storing intermediate results may be reduced.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.