CN113591025A - 特征图的处理方法、装置、卷积神经网络加速器和介质 - Google Patents
特征图的处理方法、装置、卷积神经网络加速器和介质 Download PDFInfo
- Publication number
- CN113591025A CN113591025A CN202110885650.9A CN202110885650A CN113591025A CN 113591025 A CN113591025 A CN 113591025A CN 202110885650 A CN202110885650 A CN 202110885650A CN 113591025 A CN113591025 A CN 113591025A
- Authority
- CN
- China
- Prior art keywords
- batch
- feature maps
- convolution operation
- operation result
- batches
- 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
- 238000013527 convolutional neural network Methods 0.000 title claims abstract description 16
- 238000003672 processing method Methods 0.000 title description 7
- 238000010586 diagram Methods 0.000 claims abstract description 66
- 238000000034 method Methods 0.000 claims abstract description 18
- 238000004590 computer program Methods 0.000 claims description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000009825 accumulation Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/15—Correlation function computation including computation of convolution operations
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Algebra (AREA)
- Neurology (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Complex Calculations (AREA)
Abstract
Description
Claims (10)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110885650.9A CN113591025A (zh) | 2021-08-03 | 2021-08-03 | 特征图的处理方法、装置、卷积神经网络加速器和介质 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110885650.9A CN113591025A (zh) | 2021-08-03 | 2021-08-03 | 特征图的处理方法、装置、卷积神经网络加速器和介质 |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113591025A true CN113591025A (zh) | 2021-11-02 |
Family
ID=78254303
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110885650.9A Pending CN113591025A (zh) | 2021-08-03 | 2021-08-03 | 特征图的处理方法、装置、卷积神经网络加速器和介质 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113591025A (zh) |
Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105681628A (zh) * | 2016-01-05 | 2016-06-15 | 西安交通大学 | 一种卷积网络运算单元及可重构卷积神经网络处理器和实现图像去噪处理的方法 |
CN106203617A (zh) * | 2016-06-27 | 2016-12-07 | 哈尔滨工业大学深圳研究生院 | 一种基于卷积神经网络的加速处理单元及阵列结构 |
US20180157969A1 (en) * | 2016-12-05 | 2018-06-07 | Beijing Deephi Technology Co., Ltd. | Apparatus and Method for Achieving Accelerator of Sparse Convolutional Neural Network |
CN108537330A (zh) * | 2018-03-09 | 2018-09-14 | 中国科学院自动化研究所 | 应用于神经网络的卷积计算装置及方法 |
US10083375B1 (en) * | 2017-10-13 | 2018-09-25 | StradVision, Inc. | Method and device for performing activation and convolution operation at the same time and learning method and learning device for the same |
CN108805266A (zh) * | 2018-05-21 | 2018-11-13 | 南京大学 | 一种可重构cnn高并发卷积加速器 |
CN109034249A (zh) * | 2018-07-27 | 2018-12-18 | 广州大学 | 基于分解径向对称卷积核的卷积优化方法、装置、终端设备及计算机可读存储介质 |
CN109284824A (zh) * | 2018-09-04 | 2019-01-29 | 复旦大学 | 一种基于可重构技术的用于加速卷积和池化运算的装置 |
US20190114536A1 (en) * | 2017-10-17 | 2019-04-18 | Mediatek Inc. | Hybrid non-uniform convolution transform engine for deep learning applications |
CN109993297A (zh) * | 2019-04-02 | 2019-07-09 | 南京吉相传感成像技术研究院有限公司 | 一种负载均衡的稀疏卷积神经网络加速器及其加速方法 |
CN110070178A (zh) * | 2019-04-25 | 2019-07-30 | 北京交通大学 | 一种卷积神经网络计算装置及方法 |
CN110334798A (zh) * | 2019-03-13 | 2019-10-15 | 北京地平线机器人技术研发有限公司 | 特征数据提取方法及装置、指令生成方法及装置 |
CN111047008A (zh) * | 2019-11-12 | 2020-04-21 | 天津大学 | 一种卷积神经网络加速器及加速方法 |
CN111667051A (zh) * | 2020-05-27 | 2020-09-15 | 上海赛昉科技有限公司 | 适用边缘设备的神经网络加速器及神经网络加速计算方法 |
CN111831254A (zh) * | 2019-04-15 | 2020-10-27 | 阿里巴巴集团控股有限公司 | 图像处理加速方法、图像处理模型存储方法及对应装置 |
CN112334915A (zh) * | 2018-06-25 | 2021-02-05 | 奥林巴斯株式会社 | 运算处理装置 |
CN113033794A (zh) * | 2021-03-29 | 2021-06-25 | 重庆大学 | 基于深度可分离卷积的轻量级神经网络硬件加速器 |
-
2021
- 2021-08-03 CN CN202110885650.9A patent/CN113591025A/zh active Pending
Patent Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105681628A (zh) * | 2016-01-05 | 2016-06-15 | 西安交通大学 | 一种卷积网络运算单元及可重构卷积神经网络处理器和实现图像去噪处理的方法 |
CN106203617A (zh) * | 2016-06-27 | 2016-12-07 | 哈尔滨工业大学深圳研究生院 | 一种基于卷积神经网络的加速处理单元及阵列结构 |
US20180157969A1 (en) * | 2016-12-05 | 2018-06-07 | Beijing Deephi Technology Co., Ltd. | Apparatus and Method for Achieving Accelerator of Sparse Convolutional Neural Network |
US10083375B1 (en) * | 2017-10-13 | 2018-09-25 | StradVision, Inc. | Method and device for performing activation and convolution operation at the same time and learning method and learning device for the same |
US20190114536A1 (en) * | 2017-10-17 | 2019-04-18 | Mediatek Inc. | Hybrid non-uniform convolution transform engine for deep learning applications |
CN108537330A (zh) * | 2018-03-09 | 2018-09-14 | 中国科学院自动化研究所 | 应用于神经网络的卷积计算装置及方法 |
CN108805266A (zh) * | 2018-05-21 | 2018-11-13 | 南京大学 | 一种可重构cnn高并发卷积加速器 |
CN112334915A (zh) * | 2018-06-25 | 2021-02-05 | 奥林巴斯株式会社 | 运算处理装置 |
CN109034249A (zh) * | 2018-07-27 | 2018-12-18 | 广州大学 | 基于分解径向对称卷积核的卷积优化方法、装置、终端设备及计算机可读存储介质 |
CN109284824A (zh) * | 2018-09-04 | 2019-01-29 | 复旦大学 | 一种基于可重构技术的用于加速卷积和池化运算的装置 |
CN110334798A (zh) * | 2019-03-13 | 2019-10-15 | 北京地平线机器人技术研发有限公司 | 特征数据提取方法及装置、指令生成方法及装置 |
CN109993297A (zh) * | 2019-04-02 | 2019-07-09 | 南京吉相传感成像技术研究院有限公司 | 一种负载均衡的稀疏卷积神经网络加速器及其加速方法 |
CN111831254A (zh) * | 2019-04-15 | 2020-10-27 | 阿里巴巴集团控股有限公司 | 图像处理加速方法、图像处理模型存储方法及对应装置 |
CN110070178A (zh) * | 2019-04-25 | 2019-07-30 | 北京交通大学 | 一种卷积神经网络计算装置及方法 |
CN111047008A (zh) * | 2019-11-12 | 2020-04-21 | 天津大学 | 一种卷积神经网络加速器及加速方法 |
CN111667051A (zh) * | 2020-05-27 | 2020-09-15 | 上海赛昉科技有限公司 | 适用边缘设备的神经网络加速器及神经网络加速计算方法 |
CN113033794A (zh) * | 2021-03-29 | 2021-06-25 | 重庆大学 | 基于深度可分离卷积的轻量级神经网络硬件加速器 |
Non-Patent Citations (3)
Title |
---|
李炳剑;秦国轩;朱少杰;裴智慧;: "面向卷积神经网络的FPGA加速器架构设计", 计算机科学与探索, no. 03 * |
蒋佩卿;吴丽君;: "基于FPGA的改进二值化卷积层设计", 电气开关, no. 06 * |
金光海: "快速浮点加法器的全定制设计", 计算机与现代化, no. 03, 30 March 2004 (2004-03-30) * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110197270B (zh) | 集成电路芯片装置及相关产品 | |
EP4115342A1 (en) | Parallel computing scheme generation for neural networks | |
CN108304926B (zh) | 一种适用于神经网络的池化计算装置及方法 | |
CN111062467B (zh) | 一种应用于ai异构编译器的自动切分神经网络子图方法 | |
CN111523648B (zh) | 含有聚类拓扑耦合的神经网络脉冲同步方法及系统 | |
CN113031920B (zh) | 一种芯片和用于芯片的批量模运算方法 | |
CN111651137B (zh) | 排序方法、装置、电子装置以及计算机设备 | |
CN113312183B (zh) | 面向深度神经网络的边缘计算方法 | |
CN113591025A (zh) | 特征图的处理方法、装置、卷积神经网络加速器和介质 | |
CN114065121A (zh) | 一种求解伊辛模型的计算方法及设备 | |
CN115130672B (zh) | 一种软硬件协同优化卷积神经网络计算的方法及装置 | |
CN110197274B (zh) | 集成电路芯片装置及相关产品 | |
CN113342719B (zh) | 一种运算加速单元及其运算方法 | |
JP7104183B2 (ja) | ニューラルネットワークの縮約装置 | |
CN111142840A (zh) | 基于fpga的数据计算方法和装置 | |
CN107808687B (zh) | 医疗数据获取方法、处理方法、集群处理系统及方法 | |
EP4072025A1 (en) | Decoding method and device, apparatus, and storage medium | |
Parrilla et al. | Nondeterministic AND-EXOR minimisation by using rewrite rules and simulated annealing | |
US20230035876A1 (en) | Method, apparatus, and storage medium for dividing neural network | |
Perepelkin et al. | Planning and distribution algorithm of heterogeneous resources in industrial telecommunication networks with ordered sets of tasks | |
KR102143562B1 (ko) | Ab 곱셈 및 ab^2 곱셈의 멀티 연산 장치 및 방법 | |
CN117151002A (zh) | 一种使用线性规划动态组网的方法、装置及存储介质 | |
CN110998610B (zh) | 一种信号处理方法及装置 | |
Tashev et al. | Computer simulation of the throughput of crossbar switch with modified Chang's model for load traffic | |
CN115604262A (zh) | 一种多方计算方法及电子设备 |
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 | ||
CB03 | Change of inventor or designer information |
Inventor after: Liang Youqiang Inventor after: Zhang Bin Inventor after: Hu Feng Inventor after: Liu Zhaohan Inventor after: Shen Xiaoyong Inventor after: Lv Jiangbo Inventor before: Liang Youqiang Inventor before: Zhang Bin Inventor before: Hu Feng Inventor before: Liu Zhaohan Inventor before: Yu Bei Inventor before: Shen Xiaoyong Inventor before: Lv Jiangbo Inventor before: Jia Jiaya |
|
CB03 | Change of inventor or designer information |