公开(公告)号：US20220261659A1

公开(公告)日：2022-08-18

申请号：US17738685

申请日：2022-05-06

Applicant: Huawei Technologies Co., Ltd.

Inventor： Hang Xu ,  Zhenguo Li ,  Wei Zhang ,  Xiaodan Liang ,  Chenhan Jiang

IPC: G06N3/10 ,  G06N3/08 ,  G06N3/04

Abstract: This application provides a method and related apparatus for determining a neural network in the field of artificial intelligence. The method includes: obtaining a plurality of initial search spaces; determining M candidate neural networks based on the plurality of initial search spaces, where the candidate neural network includes a plurality of candidate subnetworks, the plurality of candidate subnetworks belong to the plurality of initial search spaces, and any two of the plurality of candidate subnetworks belong to different initial search spaces; evaluating the M candidate neural networks to obtain M evaluation results; and determining N candidate neural networks from the M candidate neural networks based on the M evaluation results, and determining N first target neural networks based on the N candidate neural networks. According to the method and the related apparatus provided in this application, a combined neural network with relatively high performance can be obtained.

公开(公告)号：US20220375213A1

公开(公告)日：2022-11-24

申请号：US17880318

申请日：2022-08-03

Applicant: Huawei Technologies Co., Ltd.

Inventor： Hang Xu ,  Zhili Liu ,  Fengwei Zhou ,  Jiawei Li ,  Xiaodan Liang ,  Zhenguo Li ,  Li Qian

IPC: G06V10/82 ,  G06V10/77 ,  G06N3/063 ,  G06V10/28 ,  G06V10/774

Abstract: A processing apparatus includes a collection module and a training module, the training module includes a backbone network and a region proposal network (RPN) layer, the backbone network is connected to the RPN layer, and the RPN layer includes a class activation map (CAM) unit. The collection module is configured to obtain an image, where the image includes an image with an instance-level label and an image with an image-level label. The backbone network is used to output a feature map of the image based on the image obtained by the collection module.