Image recognition method and system based on neural network, medium and equipment

The invention provides an image recognition method and system based on a high-precision neural network, a medium and equipment. The method comprises the following steps: acquiring an image recognition exit layer by using a lightweight neural network; and taking the current image recognition exit lay...

Full description

Saved in:
Bibliographic Details
Main Authors MA YEHAN, SHEN YINGTAO, ZOU AN
Format Patent
LanguageChinese
English
Published 06.06.2023
Subjects
Online AccessGet full text

Cover

Loading…
More Information
Summary:The invention provides an image recognition method and system based on a high-precision neural network, a medium and equipment. The method comprises the following steps: acquiring an image recognition exit layer by using a lightweight neural network; and taking the current image recognition exit layer as a prediction recognition advanced exit point of the high-precision neural network, activating an exit layer of the network layer corresponding to the advanced exit point based on the advanced exit point, and obtaining a current image recognition result. According to the method, the lightweight neural network is utilized to perform image recognition based on the fusion information, the exit layer is obtained firstly, and then the exit layer of the high-precision neural network is predicted based on the exit layer obtained by the lightweight neural network, so that the cost of executing the exit layer every time by the high-precision neural network is reduced, and the calculation amount and the power consumptio
Bibliography:Application Number: CN202310301209