Neural network method and apparatus
AssigneeSamsung Electronics Co., Ltd.
InventorsSongyi HAN, Seungwon LEE, Minkyoung CHO
Life of this patent
Estimating the term…
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.
Claims16
A processor-implemented method of performing a convolution operation, the method comprising:
- obtaining input feature map data and kernel data;
- manipulating 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 manipulated kernel data.
A neural network apparatus comprising:
- one or more processors configured to:
- obtain input feature map data and kernel data,
- manipulate 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 a convolution operation, and
- perform the convolution operation based on the input feature map data and the manipulated kernel data.
Dependencies are inferred from the claim text.