公开(公告)号：US11681915B2

公开(公告)日：2023-06-20

申请号：US16897461

申请日：2020-06-10

Applicant: Samsung Electronics Co., Ltd.

Inventor： Songyi Han ,  Seungwon Lee ,  Minkyoung Cho

IPC: G06E1/00 ,  G06N3/08 ,  G06N20/10

CPC classification number: G06N3/08 ,  G06N20/10

Abstract: A processor-implemented method of performing a convolution operation is provided. The method includes obtaining input feature map data and kernel data, determine the kernel data based on a number of input channels of the input feature map, a number of output channels of an output feature map, and a number of groups of the input feature map data and a number of groups of the kernel data related to the convolution operation, and performing the convolution operation based on the input feature map data and the determined kernel data.

公开(公告)号：US12045723B2

公开(公告)日：2024-07-23

申请号：US16835532

申请日：2020-03-31

Applicant: Samsung Electronics Co., Ltd.

Inventor： Minkyoung Cho ,  Wonjo Lee ,  Seungwon Lee

IPC: G06N3/082 ,  G06N3/04

CPC classification number: G06N3/082 ,  G06N3/04

Abstract: A method and apparatus for the pruning of a neural network is provided. The method sets a weight threshold value based on a weight distribution of layers included in a neural network, predicts a change of inference accuracy of a neural network by pruning of each layer based on the weight threshold value, determines a current subject layer to be pruned with a weight threshold value among the layers included in the neural network, and prunes a determined current subject layer.

公开(公告)号：US12136254B2

公开(公告)日：2024-11-05

申请号：US17159653

申请日：2021-01-27

Applicant: Samsung Electronics Co., Ltd.

Inventor： Donghyuk Kwon ,  Minkyoung Cho

IPC: G06V10/77 ,  G06N3/04 ,  G06N3/08 ,  G06T3/40 ,  G06T7/33 ,  G06V10/94

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：US12026617B2

公开(公告)日：2024-07-02

申请号：US18144009

申请日：2023-05-05

Applicant: Samsung Electronics Co., Ltd.

Inventor： Songyi Han ,  Seungwon Lee ,  Minkyoung Cho

IPC: G09G5/00 ,  G06N3/08 ,  G06N20/10

CPC classification number: G06N3/08 ,  G06N20/10

Abstract: A processor-implemented method of performing a convolution operation is provided. The method includes obtaining input feature map data and kernel data, determine the kernel data based on a number of input channels of the input feature map, a number of output channels of an output feature map, and a number of groups of the input feature map data and a number of groups of the kernel data related to the convolution operation, and performing the convolution operation based on the input feature map data and the determined kernel data.