CNIPA.AI
검색으로 돌아가기
기록

QUANTIZATION FOR IMAGE SEGMENTATION MODEL

발명심사 중
1조회수
20청구항 · 3 독립항
§ Ⅰ

개요

발명자

Weiming YANG; Runzeng GUO; Shaoming WANG; Jun WANG; Jinkun HOU

IPC 분류

G6V 10/26G6V 10/72G6V 10/776G6V 10/82G6V 10/94G6V 40/18

CPC 분류

G6V10/273G6V10/72G6V10/776G6V10/94G6V40/193G6V10/82

A computational power evaluation result of a device is obtained. The device is to be deployed with an image segmentation model, the computational power evaluation result indicates operational performance of the device. The image segmentation model includes a plurality of operators. At least a first operator is selected from the plurality of operators based on the computational power evaluation result, a data processing duration of the first operator on the device exceeds a threshold. A quantization processing is performed on the first operator based on a difference between the data processing duration of the first operator and a desired processing duration, to obtain a first quantization operator, a data processing duration of the first quantization operator on the device is less than the desired processing duration. Based on at least the first quantization operator, the image segmentation model is converted into a target model for deployment onto the device.

원문 (중국어)

A computational power evaluation result of a device is obtained. The device is to be deployed with an image segmentation model, the computational power evaluation result indicates operational performance of the device. The image segmentation model includes a plurality of operators. At least a first operator is selected from the plurality of operators based on the computational power evaluation result, a data processing duration of the first operator on the device exceeds a threshold. A quantization processing is performed on the first operator based on a difference between the data processing duration of the first operator and a desired processing duration, to obtain a first quantization operator, a data processing duration of the first quantization operator on the device is less than the desired processing duration. Based on at least the first quantization operator, the image segmentation model is converted into a target model for deployment onto the device.