Patent · US Active

Method and apparatus for performing convolution operation for optimizing arithmetic intensity of device

US12229656B2 · kind B2 · utility

0Cited by
0References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJul 19, 2023
Grant dateFeb 18, 2025
Priority date
Expiry dateJul 19, 2043

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/063
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Provided are a method and apparatus for performing a convolution operation for optimizing the arithmetic intensity of device. The method includes obtaining input data, and generating output data through a convolution model for a device, by using the input data, wherein the convolution model includes a plurality of convolutional layers, the plurality of convolutional layers include an improved first convolutional layer that satisfies preset conditions related to latency characteristics of the device, the improved first convolutional layer is a layer obtained by adjusting a first convolutional layer so as to perform a first convolution operation on a first feature map, which is obtained by reshaping an input feature map of the first convolutional layer based on a predetermined final division value, and the final division value is determined considering the latency characteristics such that an overall arithmetic intensity of the improved first convolutional layer is increased compared to the first convolutional layer.

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