Title:
METHOD FOR TESTING DEEP LEARNING MODEL, DEVICE, AND COMPUTER STORAGE MEDIUM
Document Type and Number:
WIPO Patent Application WO/2022/246705
Kind Code:
A1
Abstract:
Disclosed in the present disclosure are a method for testing a deep learning model, a device, and a computer storage medium, providing an automated process for accelerating and testing a deep learning model. The method comprises: acquiring a deep learning model to be deployed; in response to an acceleration instruction specified by a user, accelerating the deep learning model according to an acceleration method corresponding to the acceleration instruction, so as to increase the inference speed of the deep learning model; after determining that the acceleration is complete, acquiring a test sample corresponding to the deep learning model; and testing the deep learning model by using the test sample.
Inventors:
HU PENG (CN)
Application Number:
PCT/CN2021/096132
Publication Date:
December 01, 2022
Filing Date:
May 26, 2021
Export Citation:
Assignee:
BOE TECHNOLOGY GROUP CO LTD (CN)
International Classes:
G06N3/04
Foreign References:
CN110991614A | 2020-04-10 | |||
CN111709522A | 2020-09-25 | |||
CN109213649A | 2019-01-15 | |||
CN109977813A | 2019-07-05 | |||
US20180197317A1 | 2018-07-12 | |||
US20200151289A1 | 2020-05-14 | |||
CN112835583A | 2021-05-25 |
Attorney, Agent or Firm:
TDIP & PARTNERS (CN)
Download PDF:
Previous Patent: INTER-DEVICE COMMUNICATION METHOD, CAMERA, AND DISPLAY
Next Patent: HARQ ACK FEEDBACK FOR SIDELINK COMMUNICATIONS
Next Patent: HARQ ACK FEEDBACK FOR SIDELINK COMMUNICATIONS