公开(公告)号：US20250045573A1

公开(公告)日：2025-02-06

申请号：US18709267

申请日：2022-03-03

Applicant: Intel Corporation

Inventor： Anbang YAO ,  Yikai WANG ,  Zhaole SUN ,  Yi YANG ,  Feng CHEN ,  Zhuo WANG ,  Shandong WANG ,  Yurong CHEN

IPC: G06N3/0495 ,  G06N3/0464

Abstract: The disclosure relates to decimal-bit network quantization of CNN models. Methods, apparatus, systems, and articles of manufacture for quantizing a CNN model includes, for a convolutional layer of the CNN model: allocating a 1-bit convolutional kernel subset to the convolutional layer, wherein the convolutional layer includes 32-bit or 16-bit floating-point convolutional kernels with a size of K×K and the 1-bit convolutional kernel subset includes 2N 1-bit convolutional kernel candidates with the size of K×K, 1≤N