CN111008701A - 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 - Google Patents
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 Download PDFInfo
- Publication number
- CN111008701A CN111008701A CN201911217982.9A CN201911217982A CN111008701A CN 111008701 A CN111008701 A CN 111008701A CN 201911217982 A CN201911217982 A CN 201911217982A CN 111008701 A CN111008701 A CN 111008701A
- Authority
- CN
- China
- Prior art keywords
- target layer
- output activation
- quantization
- frame
- neural network
- 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.)
- Pending
Links
- 238000013139 quantization Methods 0.000 title claims abstract description 223
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 86
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000003860 storage Methods 0.000 title claims abstract description 22
- 230000004913 activation Effects 0.000 claims abstract description 130
- 238000012545 processing Methods 0.000 claims description 26
- 238000009826 distribution Methods 0.000 claims description 25
- 238000012937 correction Methods 0.000 claims description 15
- 239000000126 substance Substances 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 5
- 238000001994 activation Methods 0.000 description 89
- 238000010586 diagram Methods 0.000 description 15
- 230000008569 process Effects 0.000 description 15
- 238000013527 convolutional neural network Methods 0.000 description 11
- 230000008901 benefit Effects 0.000 description 7
- 238000004590 computer program Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 5
- 102100030148 Integrator complex subunit 8 Human genes 0.000 description 4
- 101710092891 Integrator complex subunit 8 Proteins 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 230000006399 behavior Effects 0.000 description 2
- 230000009286 beneficial effect Effects 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
- 238000010606 normalization Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012360 testing method Methods 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
- G06N3/08—Learning methods
- G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
Abstract
Description
Claims (18)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911217982.9A CN111008701A (zh) | 2019-12-03 | 2019-12-03 | 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 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911217982.9A CN111008701A (zh) | 2019-12-03 | 2019-12-03 | 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 |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111008701A true CN111008701A (zh) | 2020-04-14 |
Family
ID=70113563
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911217982.9A Pending CN111008701A (zh) | 2019-12-03 | 2019-12-03 | 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 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111008701A (zh) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112001495A (zh) * | 2020-08-26 | 2020-11-27 | 展讯通信(上海)有限公司 | 神经网络的优化方法、系统、设备及可读存储介质 |
CN112115830A (zh) * | 2020-09-10 | 2020-12-22 | 同济大学 | 一种基于比特域特征提取的目标分布式融合识别方法 |
CN112488291A (zh) * | 2020-11-03 | 2021-03-12 | 珠海亿智电子科技有限公司 | 一种神经网络8比特量化压缩方法 |
CN113222108A (zh) * | 2021-03-09 | 2021-08-06 | 北京大学 | 目标检测的处理方法、装置及设备 |
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 |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
KR20190098671A (ko) * | 2018-02-14 | 2019-08-22 | 삼성전자주식회사 | 뉴럴 네트워크의 고속 처리 방법 및 그 방법을 이용한 장치 |
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 |
CN110198444A (zh) * | 2019-04-16 | 2019-09-03 | 浙江大华技术股份有限公司 | 视频帧编码方法、视频帧编码设备及具有存储功能的装置 |
CN110245741A (zh) * | 2018-03-09 | 2019-09-17 | 佳能株式会社 | 多层神经网络模型的优化和应用方法、装置及存储介质 |
CN110413255A (zh) * | 2018-04-28 | 2019-11-05 | 北京深鉴智能科技有限公司 | 人工神经网络调整方法和装置 |
US20190347550A1 (en) * | 2018-05-14 | 2019-11-14 | Samsung Electronics Co., Ltd. | Method and apparatus with neural network parameter quantization |
-
2019
- 2019-12-03 CN CN201911217982.9A patent/CN111008701A/zh active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
KR20190098671A (ko) * | 2018-02-14 | 2019-08-22 | 삼성전자주식회사 | 뉴럴 네트워크의 고속 처리 방법 및 그 방법을 이용한 장치 |
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 |
CN110245741A (zh) * | 2018-03-09 | 2019-09-17 | 佳能株式会社 | 多层神经网络模型的优化和应用方法、装置及存储介质 |
CN110413255A (zh) * | 2018-04-28 | 2019-11-05 | 北京深鉴智能科技有限公司 | 人工神经网络调整方法和装置 |
US20190347550A1 (en) * | 2018-05-14 | 2019-11-14 | Samsung Electronics Co., Ltd. | Method and apparatus with neural network parameter quantization |
CN110198444A (zh) * | 2019-04-16 | 2019-09-03 | 浙江大华技术股份有限公司 | 视频帧编码方法、视频帧编码设备及具有存储功能的装置 |
Cited By (8)
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 |
CN112001495A (zh) * | 2020-08-26 | 2020-11-27 | 展讯通信(上海)有限公司 | 神经网络的优化方法、系统、设备及可读存储介质 |
CN112001495B (zh) * | 2020-08-26 | 2022-11-22 | 展讯通信(上海)有限公司 | 神经网络的优化方法、系统、设备及可读存储介质 |
CN112115830A (zh) * | 2020-09-10 | 2020-12-22 | 同济大学 | 一种基于比特域特征提取的目标分布式融合识别方法 |
CN112115830B (zh) * | 2020-09-10 | 2023-06-02 | 同济大学 | 一种基于比特域特征提取的目标分布式融合识别方法 |
CN112488291A (zh) * | 2020-11-03 | 2021-03-12 | 珠海亿智电子科技有限公司 | 一种神经网络8比特量化压缩方法 |
CN113222108A (zh) * | 2021-03-09 | 2021-08-06 | 北京大学 | 目标检测的处理方法、装置及设备 |
CN113222108B (zh) * | 2021-03-09 | 2024-04-16 | 北京大学 | 目标检测的处理方法、装置及设备 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
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 | |
JP6755849B2 (ja) | 人工ニューラルネットワークのクラスに基づく枝刈り | |
US9952970B2 (en) | Cache allocation for disk array | |
US11720787B2 (en) | Method and system for training machine learning system | |
CN111401518A (zh) | 一种神经网络量化方法、装置及计算机可读存储介质 | |
US11101818B2 (en) | Method and device for storing time series data with adaptive length encoding | |
CN105183669A (zh) | 一种数据存储方法及装置 | |
US10754728B2 (en) | Accelerating system dump capturing | |
CN114528924B (zh) | 一种图像分类模型的推理方法、装置、设备及介质 | |
CN113923472B (zh) | 视频内容分析方法、装置、电子设备及存储介质 | |
KR20220097329A (ko) | 딥러닝 네트워크의 동적 양자화 정밀도 가변 알고리즘 및 방법 | |
US8375371B2 (en) | Importance-based call graph construction | |
CN110928941B (zh) | 一种数据分片抽取方法及装置 | |
US11210124B2 (en) | Movement of virtual machine data across clusters of nodes | |
US20100262756A1 (en) | Method for writing to and erasing a non-volatile memory | |
CN110968500A (zh) | 一种测试用例的执行方法及装置 | |
CN108958658B (zh) | 一种目标数据的获取方法及装置 | |
CN113052292A (zh) | 卷积神经网络技术方法、装置及计算机可读存储介质 | |
CN112905189A (zh) | 模型翻译方法、装置及计算机可读存储介质 | |
CN113298225A (zh) | 数据处理方法、音频降噪方法和神经网络模型 | |
CN113936698B (zh) | 音频数据的处理方法、装置以及电子设备 | |
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 | |
US11431349B2 (en) | Method, electronic device and computer program product for processing data | |
JP2023035911A (ja) | 人工知能モデルを訓練する方法、コンピュータシステム、コンピュータプログラム(管理限界を使用して人工知能モデル訓練を早期停止すること) | |
CN115700539A (zh) | 一种解决计数问题的方法及相关设备 |
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: 20201203 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: 20240507 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 |