公开(公告)号：US20210406646A1

公开(公告)日：2021-12-30

申请号：US17091338

申请日：2020-11-06

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Songyi HAN ,  Sangwon HA ,  Donghyuk KWON

IPC: G06N3/06 ,  G06N3/08 ,  G06K9/62 ,  G06F9/38

Abstract: A processor-implemented tensor processing method includes: receiving a request to process a neural network including a normalization layer by an accelerator; and generating an instruction executable by the accelerator in response to the request, wherein, by executing the instruction, the accelerator is configured to determine an intermediate tensor corresponding to a result of a portion of operations of the normalization layer, by performing, in a channel axis direction, a convolution based on an input tensor and a kernel, wherein the input tensor is of the normalization layer and includes a plurality of channels, a number of input channels of the kernel is determined based on the input tensor, and scaling values of elements of the kernel are determined based on the number of input channels.

公开(公告)号：US20220067429A1

公开(公告)日：2022-03-03

申请号：US17159653

申请日：2021-01-27

Applicant: Samsung Electronics Co., Ltd.

Inventor： Donghyuk KWON ,  Minkyoung CHO

IPC: G06K9/62 ,  G06T3/40 ,  G06T7/33 ,  G06K9/00 ,  G06N3/04 ,  G06N3/08

Abstract: An image processing method and apparatus are provided. The image processing method includes obtaining a kernel that is deterministically defined based on an extension ratio of a first feature map, up-sampling the first feature map to a second feature map by performing a transposed convolution operation between the first feature map and the kernel, and outputting the second feature map.

公开(公告)号：US20230065528A1

公开(公告)日：2023-03-02

申请号：US17883987

申请日：2022-08-09

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hyeongseok YU ,  Donghyuk KWON ,  Channoh KIM ,  Seongwook PARK ,  Yeongon CHO

IPC: G06F7/491 ,  G06F7/48

Abstract: An apparatus with multi-format data support includes: a receiver configured to receive a plurality of data corresponding to a plurality of data formats; one or more processors configured to: multiply the plurality of data using one or more multipliers; perform a first alignment on a result of the multiplication based on an exponent value of the plurality of data; add a result of the first alignment; and perform a second alignment on a result of the addition based on the exponent value and an operation result of a previous cycle.

公开(公告)号：US20210097347A1

公开(公告)日：2021-04-01

申请号：US16804672

申请日：2020-02-28

Applicant: Samsung Electronics Co., Ltd.

Inventor： Donghyuk KWON ,  Seungwon LEE

IPC: G06K9/62 ,  G06N3/08 ,  G06N3/04

Abstract: A processor-implemented data processing method includes: predicting whether there will be an inefficient section, of a neural network set to be implemented, during a processing of data, based on a hardware configuration for processing the data; adjusting a layer parameter corresponding to the inefficient section of the neural network; and processing the data using the neural network with the adjusted layer parameter.