CN111401518A - 一种神经网络量化方法、装置及计算机可读存储介质 - Google Patents
一种神经网络量化方法、装置及计算机可读存储介质 Download PDFInfo
- Publication number
- CN111401518A CN111401518A CN202010143410.7A CN202010143410A CN111401518A CN 111401518 A CN111401518 A CN 111401518A CN 202010143410 A CN202010143410 A CN 202010143410A CN 111401518 A CN111401518 A CN 111401518A
- Authority
- CN
- China
- Prior art keywords
- quantization
- target
- determining
- distribution data
- network layer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000013139 quantization Methods 0.000 title claims abstract description 389
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 60
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000003860 storage Methods 0.000 title claims abstract description 22
- 238000009826 distribution Methods 0.000 claims abstract description 227
- 230000004913 activation Effects 0.000 claims abstract description 125
- 238000012937 correction Methods 0.000 claims abstract description 32
- 238000012545 processing Methods 0.000 claims description 19
- 238000001914 filtration Methods 0.000 claims description 6
- 239000000126 substance Substances 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 21
- 230000008901 benefit Effects 0.000 description 7
- 238000004590 computer program Methods 0.000 description 7
- 102100030148 Integrator complex subunit 8 Human genes 0.000 description 6
- 101710092891 Integrator complex subunit 8 Proteins 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 230000003213 activating effect Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- VKYKSIONXSXAKP-UHFFFAOYSA-N hexamethylenetetramine Chemical compound C1N(C2)CN3CN1CN2C3 VKYKSIONXSXAKP-UHFFFAOYSA-N 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
- G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Neurology (AREA)
- Compression Or Coding Systems Of Tv Signals (AREA)
Abstract
Description
Claims (14)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010143410.7A CN111401518B (zh) | 2020-03-04 | 一种神经网络量化方法、装置及计算机可读存储介质 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010143410.7A CN111401518B (zh) | 2020-03-04 | 一种神经网络量化方法、装置及计算机可读存储介质 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111401518A true CN111401518A (zh) | 2020-07-10 |
CN111401518B CN111401518B (zh) | 2024-06-04 |
Family
ID=
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112200275A (zh) * | 2020-12-09 | 2021-01-08 | 上海齐感电子信息科技有限公司 | 人工神经网络的量化方法及装置 |
WO2022027862A1 (zh) * | 2020-08-07 | 2022-02-10 | 嘉楠明芯(北京)科技有限公司 | 神经网络模型量化方法以及装置 |
WO2022148071A1 (zh) * | 2021-01-07 | 2022-07-14 | 苏州浪潮智能科技有限公司 | 一种图像特征提取方法、装置、设备及存储介质 |
WO2022230906A1 (ja) * | 2021-04-28 | 2022-11-03 | LeapMind株式会社 | ニューラルネットワーク生成装置、ニューラルネットワーク演算装置、エッジデバイス、ニューラルネットワーク制御方法およびソフトウェア生成プログラム |
Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105138304A (zh) * | 2015-07-28 | 2015-12-09 | 北京华力创通科技股份有限公司 | 数字信号的自适应量化方法及装置 |
DE102018101166A1 (de) * | 2017-01-20 | 2018-07-26 | Nvidia Corporation | Automatisierte verfahren zur umwandlung in ein datenformat geringerer genauigkeit |
CN108337000A (zh) * | 2017-01-20 | 2018-07-27 | 辉达公司 | 用于转换到较低精度数据格式的自动方法 |
CN108537322A (zh) * | 2018-03-16 | 2018-09-14 | 新智认知数据服务有限公司 | 神经网络层间激活值量化方法及装置 |
US20190049540A1 (en) * | 2017-08-10 | 2019-02-14 | Siemens Healthcare Gmbh | Image standardization using generative adversarial networks |
CN109389219A (zh) * | 2017-08-04 | 2019-02-26 | 三星电子株式会社 | 用于对神经网络的参数进行量化的方法和装置 |
CN109446953A (zh) * | 2018-10-17 | 2019-03-08 | 福州大学 | 一种基于轻量化卷积神经网络的行人重识别方法 |
CN109558945A (zh) * | 2017-09-25 | 2019-04-02 | 三星电子株式会社 | 对人工神经网络及浮点神经网络进行量化的方法及装置 |
CN109583561A (zh) * | 2017-09-28 | 2019-04-05 | 杭州海康威视数字技术股份有限公司 | 一种深度神经网络的激活量量化方法及装置 |
CN110008952A (zh) * | 2019-03-26 | 2019-07-12 | 深兰科技(上海)有限公司 | 一种目标识别方法及设备 |
CN110096968A (zh) * | 2019-04-10 | 2019-08-06 | 西安电子科技大学 | 一种基于深度模型优化的超高速静态手势识别方法 |
CN110163240A (zh) * | 2018-02-14 | 2019-08-23 | 三星电子株式会社 | 对象识别方法及设备 |
CN110210619A (zh) * | 2019-05-22 | 2019-09-06 | 上海商汤智能科技有限公司 | 神经网络的训练方法及装置、电子设备和存储介质 |
WO2019184823A1 (zh) * | 2018-03-26 | 2019-10-03 | 华为技术有限公司 | 基于卷积神经网络模型的图像处理方法和装置 |
US20190347550A1 (en) * | 2018-05-14 | 2019-11-14 | Samsung Electronics Co., Ltd. | Method and apparatus with neural network parameter quantization |
KR20190129422A (ko) * | 2018-05-11 | 2019-11-20 | 서울대학교산학협력단 | 뉴럴 네트워크를 이용한 변분 추론 방법 및 장치 |
CN110610237A (zh) * | 2019-09-17 | 2019-12-24 | 普联技术有限公司 | 模型的量化训练方法、装置及存储介质 |
Patent Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105138304A (zh) * | 2015-07-28 | 2015-12-09 | 北京华力创通科技股份有限公司 | 数字信号的自适应量化方法及装置 |
DE102018101166A1 (de) * | 2017-01-20 | 2018-07-26 | Nvidia Corporation | Automatisierte verfahren zur umwandlung in ein datenformat geringerer genauigkeit |
CN108337000A (zh) * | 2017-01-20 | 2018-07-27 | 辉达公司 | 用于转换到较低精度数据格式的自动方法 |
CN109389219A (zh) * | 2017-08-04 | 2019-02-26 | 三星电子株式会社 | 用于对神经网络的参数进行量化的方法和装置 |
US20190049540A1 (en) * | 2017-08-10 | 2019-02-14 | Siemens Healthcare Gmbh | Image standardization using generative adversarial networks |
CN109558945A (zh) * | 2017-09-25 | 2019-04-02 | 三星电子株式会社 | 对人工神经网络及浮点神经网络进行量化的方法及装置 |
CN109583561A (zh) * | 2017-09-28 | 2019-04-05 | 杭州海康威视数字技术股份有限公司 | 一种深度神经网络的激活量量化方法及装置 |
CN110163240A (zh) * | 2018-02-14 | 2019-08-23 | 三星电子株式会社 | 对象识别方法及设备 |
CN108537322A (zh) * | 2018-03-16 | 2018-09-14 | 新智认知数据服务有限公司 | 神经网络层间激活值量化方法及装置 |
WO2019184823A1 (zh) * | 2018-03-26 | 2019-10-03 | 华为技术有限公司 | 基于卷积神经网络模型的图像处理方法和装置 |
KR20190129422A (ko) * | 2018-05-11 | 2019-11-20 | 서울대학교산학협력단 | 뉴럴 네트워크를 이용한 변분 추론 방법 및 장치 |
US20190347550A1 (en) * | 2018-05-14 | 2019-11-14 | Samsung Electronics Co., Ltd. | Method and apparatus with neural network parameter quantization |
CN109446953A (zh) * | 2018-10-17 | 2019-03-08 | 福州大学 | 一种基于轻量化卷积神经网络的行人重识别方法 |
CN110008952A (zh) * | 2019-03-26 | 2019-07-12 | 深兰科技(上海)有限公司 | 一种目标识别方法及设备 |
CN110096968A (zh) * | 2019-04-10 | 2019-08-06 | 西安电子科技大学 | 一种基于深度模型优化的超高速静态手势识别方法 |
CN110210619A (zh) * | 2019-05-22 | 2019-09-06 | 上海商汤智能科技有限公司 | 神经网络的训练方法及装置、电子设备和存储介质 |
CN110610237A (zh) * | 2019-09-17 | 2019-12-24 | 普联技术有限公司 | 模型的量化训练方法、装置及存储介质 |
Non-Patent Citations (2)
Title |
---|
HONGXIANG FAN等: "Static Block Floating-Point Quantization for Convolutional Neural Networks on FPGA", 《2019 INTERNATIONAL CONFERENCE ON FIELD-PROGRAMMABLE TECHNOLOGY (ICFPT)》, pages 28 - 35 * |
黄蓉: "适于工程化实现的卷积神经网络算法研究", 《中国优秀硕士学位论文电子期刊》, pages 39 - 48 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2022027862A1 (zh) * | 2020-08-07 | 2022-02-10 | 嘉楠明芯(北京)科技有限公司 | 神经网络模型量化方法以及装置 |
CN112200275A (zh) * | 2020-12-09 | 2021-01-08 | 上海齐感电子信息科技有限公司 | 人工神经网络的量化方法及装置 |
WO2022148071A1 (zh) * | 2021-01-07 | 2022-07-14 | 苏州浪潮智能科技有限公司 | 一种图像特征提取方法、装置、设备及存储介质 |
WO2022230906A1 (ja) * | 2021-04-28 | 2022-11-03 | LeapMind株式会社 | ニューラルネットワーク生成装置、ニューラルネットワーク演算装置、エッジデバイス、ニューラルネットワーク制御方法およびソフトウェア生成プログラム |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10025773B2 (en) | System and method for natural language processing using synthetic text | |
US11720787B2 (en) | Method and system for training machine learning system | |
CN111008701A (zh) | 一种基于神经网络的数据量化方法、装置及计算机可读存储介质 | |
US20200395954A1 (en) | Method and device for storing time series data with adaptive length encoding | |
CN114528924B (zh) | 一种图像分类模型的推理方法、装置、设备及介质 | |
CN110827208A (zh) | 卷积神经网络的通用池化增强方法、装置、设备及介质 | |
CN112861996A (zh) | 深度神经网络模型压缩方法及装置、电子设备、存储介质 | |
CN111860771A (zh) | 一种应用于边缘计算的卷积神经网络计算方法 | |
CN111401518A (zh) | 一种神经网络量化方法、装置及计算机可读存储介质 | |
CN111401518B (zh) | 一种神经网络量化方法、装置及计算机可读存储介质 | |
US10032460B2 (en) | Frequency envelope vector quantization method and apparatus | |
CN114385092B (zh) | 固态硬盘闪存阵列的擦除方法、固态硬盘主控芯片 | |
CN112749783A (zh) | 一种神经网络模型的量化方法、装置及计算机可读存储介质 | |
CN108958658B (zh) | 一种目标数据的获取方法及装置 | |
EP4295276A1 (en) | Accelerated execution of convolution operation by convolutional neural network | |
CN112905189A (zh) | 模型翻译方法、装置及计算机可读存储介质 | |
CN115034351A (zh) | 数据处理方法、卷积神经网络训练方法、装置和fpga | |
CN114817500B (zh) | 一种基于量化的长文本问答推理方法、设备及介质 | |
CN117934323B (zh) | 图像生成方法、装置、电子设备及存储介质 | |
CN109144424B (zh) | 一种固态硬盘的读写方法、装置、设备及存储介质 | |
CN111767980B (zh) | 模型优化方法、装置及设备 | |
CN113052292B (zh) | 卷积神经网络技术方法、装置及计算机可读存储介质 | |
CN111488969B (zh) | 基于神经网络加速器的执行优化方法及装置 | |
CN114817500A (zh) | 一种基于量化的长文本问答推理方法、设备及介质 | |
CN117976024A (zh) | 一种用于集成电路测试机中测试向量的替换方法及系统 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20201202 Address after: Room 206, 2 / F, building C, phase I, Zhongguancun Software Park, No. 8, Dongbei Wangxi Road, Haidian District, Beijing 100094 Applicant after: Canaan Bright Sight Co.,Ltd. Address before: 310000, room 12, building 4, building nine, No. nine, 1203 Ring Road, Hangzhou, Zhejiang, Jianggan District Applicant before: Hangzhou Canaan Creative Information Technology Ltd. |
|
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20240430 Address after: Room 101, 20th Floor, Building 1, Zone 1, No. 81 Beiqing Road, Haidian District, Beijing, 100094 Applicant after: Beijing Sisheng Technology Co.,Ltd. Country or region after: China Address before: Room 206, 2 / F, building C, phase I, Zhongguancun Software Park, No. 8, Dongbei Wangxi Road, Haidian District, Beijing 100094 Applicant before: Canaan Bright Sight Co.,Ltd. Country or region before: China |
|
TA01 | Transfer of patent application right | ||
GR01 | Patent grant |