CN110322008A - 一种基于残差卷积神经网络的量化处理方法及装置 - Google Patents
一种基于残差卷积神经网络的量化处理方法及装置 Download PDFInfo
- Publication number
- CN110322008A CN110322008A CN201910619503.XA CN201910619503A CN110322008A CN 110322008 A CN110322008 A CN 110322008A CN 201910619503 A CN201910619503 A CN 201910619503A CN 110322008 A CN110322008 A CN 110322008A
- Authority
- CN
- China
- Prior art keywords
- data
- quantization
- point
- layers
- convolutional neural
- 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 210
- 238000003672 processing method Methods 0.000 title abstract description 3
- 238000013528 artificial neural network Methods 0.000 title description 4
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 76
- 238000000034 method Methods 0.000 claims abstract description 64
- 230000006399 behavior Effects 0.000 claims description 6
- 238000011002 quantification Methods 0.000 claims description 5
- 230000009471 action Effects 0.000 claims description 2
- 238000005265 energy consumption Methods 0.000 abstract 1
- 230000008859 change Effects 0.000 description 17
- 238000010586 diagram Methods 0.000 description 16
- 230000008569 process Effects 0.000 description 11
- 238000004364 calculation method Methods 0.000 description 9
- 238000012545 processing Methods 0.000 description 7
- 238000005498 polishing Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000006073 displacement reaction Methods 0.000 description 4
- 230000001537 neural effect Effects 0.000 description 4
- 230000009466 transformation Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000004321 preservation Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000003321 amplification Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
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
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)
- Compression, Expansion, Code Conversion, And Decoders (AREA)
Abstract
Description
Claims (10)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910619503.XA CN110322008A (zh) | 2019-07-10 | 2019-07-10 | 一种基于残差卷积神经网络的量化处理方法及装置 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910619503.XA CN110322008A (zh) | 2019-07-10 | 2019-07-10 | 一种基于残差卷积神经网络的量化处理方法及装置 |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110322008A true CN110322008A (zh) | 2019-10-11 |
Family
ID=68123250
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910619503.XA Pending CN110322008A (zh) | 2019-07-10 | 2019-07-10 | 一种基于残差卷积神经网络的量化处理方法及装置 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110322008A (zh) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111260022A (zh) * | 2019-11-22 | 2020-06-09 | 中国电子科技集团公司第五十二研究所 | 一种卷积神经网络全int8定点量化的方法 |
CN111461302A (zh) * | 2020-03-30 | 2020-07-28 | 杭州嘉楠耘智信息科技有限公司 | 一种基于卷积神经网络的数据处理方法、设备及存储介质 |
CN113780513A (zh) * | 2020-06-10 | 2021-12-10 | 杭州海康威视数字技术股份有限公司 | 网络模型量化、推理方法、装置、电子设备及存储介质 |
US20220092383A1 (en) * | 2020-09-18 | 2022-03-24 | Samsung Electronics Co., Ltd. | System and method for post-training quantization of deep neural networks with per-channel quantization mode selection |
WO2022088063A1 (zh) * | 2020-10-30 | 2022-05-05 | 华为技术有限公司 | 神经网络模型的量化方法和装置、数据处理的方法和装置 |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20010017941A1 (en) * | 1997-03-14 | 2001-08-30 | Navin Chaddha | Method and apparatus for table-based compression with embedded coding |
CN106485316A (zh) * | 2016-10-31 | 2017-03-08 | 北京百度网讯科技有限公司 | 神经网络模型压缩方法以及装置 |
CN106951962A (zh) * | 2017-03-22 | 2017-07-14 | 北京地平线信息技术有限公司 | 用于神经网络的复合运算单元、方法和电子设备 |
CN107644254A (zh) * | 2017-09-09 | 2018-01-30 | 复旦大学 | 一种卷积神经网络权重参数量化训练方法及系统 |
CN108491926A (zh) * | 2018-03-05 | 2018-09-04 | 东南大学 | 一种基于对数量化的低比特高效深度卷积神经网络硬件加速设计方法、模块及系统 |
CN108734287A (zh) * | 2017-04-21 | 2018-11-02 | 展讯通信(上海)有限公司 | 深度神经网络模型的压缩方法及装置、终端、存储介质 |
-
2019
- 2019-07-10 CN CN201910619503.XA patent/CN110322008A/zh active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20010017941A1 (en) * | 1997-03-14 | 2001-08-30 | Navin Chaddha | Method and apparatus for table-based compression with embedded coding |
CN106485316A (zh) * | 2016-10-31 | 2017-03-08 | 北京百度网讯科技有限公司 | 神经网络模型压缩方法以及装置 |
CN106951962A (zh) * | 2017-03-22 | 2017-07-14 | 北京地平线信息技术有限公司 | 用于神经网络的复合运算单元、方法和电子设备 |
CN108734287A (zh) * | 2017-04-21 | 2018-11-02 | 展讯通信(上海)有限公司 | 深度神经网络模型的压缩方法及装置、终端、存储介质 |
CN107644254A (zh) * | 2017-09-09 | 2018-01-30 | 复旦大学 | 一种卷积神经网络权重参数量化训练方法及系统 |
CN108491926A (zh) * | 2018-03-05 | 2018-09-04 | 东南大学 | 一种基于对数量化的低比特高效深度卷积神经网络硬件加速设计方法、模块及系统 |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111260022A (zh) * | 2019-11-22 | 2020-06-09 | 中国电子科技集团公司第五十二研究所 | 一种卷积神经网络全int8定点量化的方法 |
CN111260022B (zh) * | 2019-11-22 | 2023-09-05 | 中国电子科技集团公司第五十二研究所 | 一种卷积神经网络全int8定点量化的方法 |
CN111461302A (zh) * | 2020-03-30 | 2020-07-28 | 杭州嘉楠耘智信息科技有限公司 | 一种基于卷积神经网络的数据处理方法、设备及存储介质 |
CN111461302B (zh) * | 2020-03-30 | 2024-04-19 | 嘉楠明芯(北京)科技有限公司 | 一种基于卷积神经网络的数据处理方法、设备及存储介质 |
CN113780513A (zh) * | 2020-06-10 | 2021-12-10 | 杭州海康威视数字技术股份有限公司 | 网络模型量化、推理方法、装置、电子设备及存储介质 |
CN113780513B (zh) * | 2020-06-10 | 2024-05-03 | 杭州海康威视数字技术股份有限公司 | 网络模型量化、推理方法、装置、电子设备及存储介质 |
US20220092383A1 (en) * | 2020-09-18 | 2022-03-24 | Samsung Electronics Co., Ltd. | System and method for post-training quantization of deep neural networks with per-channel quantization mode selection |
WO2022088063A1 (zh) * | 2020-10-30 | 2022-05-05 | 华为技术有限公司 | 神经网络模型的量化方法和装置、数据处理的方法和装置 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110322008A (zh) | 一种基于残差卷积神经网络的量化处理方法及装置 | |
US11928177B2 (en) | Methods and apparatus for performing video processing matrix operations within a memory array | |
US20210357736A1 (en) | Deep neural network hardware accelerator based on power exponential quantization | |
EP3754561A1 (en) | Reconfigurable memory compression techniques for deep neural networks | |
CN107169563B (zh) | 应用于二值权重卷积网络的处理系统及方法 | |
US20200349217A1 (en) | Methods and apparatus for performing matrix transformations within a memory array | |
CN111126579B (zh) | 一种适用于二值卷积神经网络计算的存内计算装置 | |
CN107578095A (zh) | 神经网络计算装置及包含该计算装置的处理器 | |
CN108446764B (zh) | 一种新型神经形态芯片架构 | |
CN105049061A (zh) | 基于超前计算的高维基极化码译码器和极化码译码方法 | |
CN112329910B (zh) | 一种面向结构剪枝结合量化的深度卷积神经网络压缩方法 | |
CN113222150B (zh) | 一种量子态的变换方法及装置 | |
US20210209450A1 (en) | Compressed weight distribution in networks of neural processors | |
CN108491924B (zh) | 一种面向人工智能计算的神经网络数据串行流水处理装置 | |
Tsai et al. | RePIM: Joint exploitation of activation and weight repetitions for in-ReRAM DNN acceleration | |
CN109697509B (zh) | 处理方法及装置、运算方法及装置 | |
CN113222129A (zh) | 一种基于多级缓存循环利用的卷积运算处理单元及系统 | |
CN110766136B (zh) | 一种稀疏矩阵与向量的压缩方法 | |
CN110085270B (zh) | 存储运算电路模块及处理器 | |
CN112561049A (zh) | 一种基于忆阻器的dnn加速器的资源分配方法及装置 | |
CN109669666A (zh) | 乘累加处理器 | |
CN113128688B (zh) | 通用型ai并行推理加速结构以及推理设备 | |
Manikandan et al. | Approximation computing techniques to accelerate CNN based image processing applications–a survey in hardware/software perspective | |
CN113392963B (zh) | 基于fpga的cnn硬件加速系统设计方法 | |
US20210357184A1 (en) | Device for computing an inner product |
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: 20201130 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: 20240508 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 |