公开(公告)号：US20250117637A1

公开(公告)日：2025-04-10

申请号：US18961921

申请日：2024-11-27

Applicant: Huawei Technologies Co., Ltd.

Inventor： Ying Nie ,  Kai Han ,  Chuanjian Liu ,  Junhui Ma ,  Yunhe Wang

IPC: G06N3/0495

Abstract: A neural network parameter quantization method includes obtaining a parameter of each neuron in a to-be-quantized model to obtain a parameter set, clustering parameters in the parameter set to obtain types of classified data, and quantizing each type of classified data in the types of classified data to obtain at least one type of quantization parameter, where the at least one type of quantization parameter is used to obtain a compression model, and precision of the at least one type of quantization parameter is lower than precision of a parameter in the to-be-quantized model.

公开(公告)号：US20240005164A1

公开(公告)日：2024-01-04

申请号：US18362435

申请日：2023-07-31

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yixing Xu ,  Kai Han ,  Yehui Tang ,  Yunhe Wang ,  Chunjing Xu

IPC: G06N3/084 ,  G06N3/04

CPC classification number: G06N3/084 ,  G06N3/04

Abstract: A neural network training method includes performing, in a forward propagation process, binarization processing on a target weight by using a binarization function, and using data obtained through the binarization processing as a weight of a first neural network layer in a neural network; and calculating, in a backward propagation process, a gradient of a loss function with respect to the target weight by using a gradient of a fitting function as a gradient of the binarization function.

公开(公告)号：US20230143985A1

公开(公告)日：2023-05-11

申请号：US18148304

申请日：2022-12-29

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Kai Han ,  Yunhe Wang ,  Chunjing Xu

IPC: G06N3/084 ,  G06N3/0464

CPC classification number: G06N3/084 ,  G06N3/0464 ,  G06V10/82

Abstract: A data feature extraction method and apparatus in the field of artificial intelligence are provided. An addition convolution operation is performed to extract a target feature in quantized data based on quantized feature extraction parameters, that is, to calculate a sum of absolute values of differences between the quantized feature extraction parameters and the quantized data, to obtain the target feature based on the sum. In addition, feature extraction parameters and data are quantized by using a same quantization parameter. According to this application, a storage resource is saved, a computing resource is saved, thereby reducing a limitation on an application of artificial intelligence to a resource-limited device. Further, when the extracted feature data is dequantized, the feature data may be dequantized based on the quantization parameters.

公开(公告)号：US12243284B2

公开(公告)日：2025-03-04

申请号：US17587689

申请日：2022-01-28

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Kai Han ,  Yunhe Wang ,  Han Shu ,  Chunjing Xu

IPC: G06V10/00 ,  G06V10/44 ,  G06V10/764 ,  G06V10/82

Abstract: This application relates to an image recognition technology in the field of computer vision in the field of artificial intelligence, and provides an image classification method and apparatus. The method includes: obtaining an input feature map of a to-be-processed image; performing convolution processing on the input feature map based on M convolution kernels of a neural network, to obtain a candidate output feature map of M channels, where M is a positive integer; performing matrix transformation on the M channels of the candidate output feature map based on N matrices, to obtain an output feature map of N channels, where a quantity of channels of each of the N matrices is less than M, N is greater than M, and N is a positive integer; and classify the to-be-processed image based on the output feature map, to obtain a classification result of the to-be-processed image.

公开(公告)号：US12254064B2

公开(公告)日：2025-03-18

申请号：US17488735

申请日：2021-09-29

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Hanting Chen ,  Yunhe Wang ,  Chuanjian Liu ,  Kai Han ,  Chunjing Xu

IPC: G06F18/214 ,  G06F18/243 ,  G06N3/047

Abstract: The present application discloses an image generation method, a neural network compression method, and a related apparatus and device in the field of artificial intelligence. The image generation method includes: inputting a first matrix into an initial image generator to obtain a generated image; inputting the generated image into a preset discriminator to obtain a determining result, where the preset discriminator is obtained through training based on a real image and a category corresponding to the real image; updating the initial image generator based on the determining result to obtain a target image generator; and further inputting a second matrix into the target image generator to obtain a sample image. Further, a neural network compression method is disclosed, to compress the preset discriminator based on the sample image obtained by using the foregoing image generation method.

公开(公告)号：US10891537B2

公开(公告)日：2021-01-12

申请号：US16359346

申请日：2019-03-20

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Yunhe Wang ,  Chunjing Xu ,  Kai Han

IPC: G06N3/04 ,  G06F17/15 ,  G06F17/16

Abstract: This application discloses a convolutional neural network-based image processing method and image processing apparatus in the artificial intelligence field. The method may include: receiving an input image; preprocessing the input image to obtain preprocessed image information; and performing convolution on the image information using a convolutional neural network, and outputting a convolution result. In embodiments of this application, the image processing apparatus may store primary convolution kernels of convolution layers, and before performing convolution using the convolution layers, generate secondary convolution kernels using the primary convolution kernels of the convolution layers.