公开(公告)号：US20230177308A1

公开(公告)日：2023-06-08

申请号：US17743906

申请日：2022-05-13

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： WONHEE LEE

IPC: G06N3/04 ,  G06F7/50

CPC classification number: G06N3/04 ,  G06F7/50

Abstract: Disclosed is a method and apparatus for searching for an optimal architecture of a neural network. The apparatus may include a processor configured to generate a neural network loss based on parameters of a candidate architecture for the neural network, measure first hardware resources used in operation of the neural network with the candidate architecture, generate a prediction, using a hardware resource prediction model, of second hardware resources that would be used for operating the neural network with the candidate architecture, determine a hardware resource loss based on the first hardware resources and the second hardware resources, and determine a target architecture of the neural network based on the neural network loss and the hardware resource loss.

公开(公告)号：US20170200284A1

公开(公告)日：2017-07-13

申请号：US15384616

申请日：2016-12-20

Applicant: Samsung Electronics Co., Ltd.

Inventor： WONHEE LEE ,  Young Hun SUNG ,  Soochul LIM

IPC: G06T7/593 ,  H04N13/00 ,  H04N13/02

CPC classification number: G06T7/593 ,  G06T2207/10028 ,  G06T2207/20081 ,  G06T2207/20084 ,  H04N13/128 ,  H04N13/156 ,  H04N13/204 ,  H04N13/239 ,  H04N2013/0081

Abstract: A method and apparatus for estimating a depth, and a method and apparatus for training an distance estimator are provided, wherein the method for estimating a depth may include obtaining an image, and estimating a depth of a second image object based on a correlation between a first image object and the second image object in the image and a depth of the first image object.