公开(公告)号：US20230042397A1

公开(公告)日：2023-02-09

申请号：US17758166

申请日：2020-11-19

Applicant: Huawei Technologies Co., Ltd.

Inventor： Qinghua YU ,  Mohan LIU ,  Zhicheng SUI ,  Li ZHOU ,  Lixun BAI

IPC: G06N5/04 ,  G06N3/08 ,  G06N3/04 ,  G06N3/063

Abstract: This application relates to the field of artificial intelligence technologies, and discloses a machine learning model search method, a related apparatus, and a device. In the method, before model search and quantization, a plurality of single bit models are generated based on a to-be-quantized model, and evaluation parameters of layer structures in the plurality of single bit models are obtained. Further, after a candidate model selected from a candidate set is trained and tested, to obtain a target model, a quantization weight of each layer structure in the target model may be determined based on a network structure of the target model and evaluation parameters of all layer structures in the target model, a layer structure with a maximum quantization weight in the target model is quantized, and a model obtained through quantization is added to the candidate set.