公开(公告)号：US20230137502A1

公开(公告)日：2023-05-04

申请号：US18091704

申请日：2022-12-30

Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventor： Yingyu JI ,  Yanlong ZHANG ,  Jingjing SUN

IPC: G06T5/30 ,  G06T7/70

Abstract: A method for processing a feature image includes: grouping parameters in a parameter matrix to obtain a plurality of arrays; the parameter matrix being a matrix converted and obtained from a convolutional layer in a convolutional neural network; performing thinning processing on the parameter matrix according to parameter values in the plurality of arrays to obtain a thinned parameter matrix; performing calculation by using the thinned parameter matrix and a data matrix to determine an output feature map corresponding to the convolutional layer in the case where a sparsity of the thinned parameter matrix satisfies a predetermined condition; the data matrix including a matrix converted and obtained from an input feature map inputted into the convolutional layer.