CN109359728B - 计算神经网络压缩最佳定点位数的方法、存储介质和装置 - Google Patents
计算神经网络压缩最佳定点位数的方法、存储介质和装置 Download PDFInfo
- Publication number
- CN109359728B CN109359728B CN201810992672.3A CN201810992672A CN109359728B CN 109359728 B CN109359728 B CN 109359728B CN 201810992672 A CN201810992672 A CN 201810992672A CN 109359728 B CN109359728 B CN 109359728B
- Authority
- CN
- China
- Prior art keywords
- fixed
- point
- deep learning
- learning algorithm
- current
- 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.)
- Active
Links
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
- G06N3/06—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
- G06N3/04—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
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Neurology (AREA)
- Image Analysis (AREA)
Abstract
Description
Claims (8)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810992672.3A CN109359728B (zh) | 2018-08-29 | 2018-08-29 | 计算神经网络压缩最佳定点位数的方法、存储介质和装置 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810992672.3A CN109359728B (zh) | 2018-08-29 | 2018-08-29 | 计算神经网络压缩最佳定点位数的方法、存储介质和装置 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109359728A CN109359728A (zh) | 2019-02-19 |
CN109359728B true CN109359728B (zh) | 2021-04-09 |
Family
ID=65350094
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810992672.3A Active CN109359728B (zh) | 2018-08-29 | 2018-08-29 | 计算神经网络压缩最佳定点位数的方法、存储介质和装置 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109359728B (zh) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106845640A (zh) * | 2017-01-12 | 2017-06-13 | 南京大学 | 基于深度卷积神经网络的层内非均匀的等间隔定点量化方法 |
CN107239829A (zh) * | 2016-08-12 | 2017-10-10 | 北京深鉴科技有限公司 | 一种优化人工神经网络的方法 |
CN107480770A (zh) * | 2017-07-27 | 2017-12-15 | 中国科学院自动化研究所 | 可调节量化位宽的神经网络量化与压缩的方法及装置 |
-
2018
- 2018-08-29 CN CN201810992672.3A patent/CN109359728B/zh active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107239829A (zh) * | 2016-08-12 | 2017-10-10 | 北京深鉴科技有限公司 | 一种优化人工神经网络的方法 |
CN106845640A (zh) * | 2017-01-12 | 2017-06-13 | 南京大学 | 基于深度卷积神经网络的层内非均匀的等间隔定点量化方法 |
CN107480770A (zh) * | 2017-07-27 | 2017-12-15 | 中国科学院自动化研究所 | 可调节量化位宽的神经网络量化与压缩的方法及装置 |
Non-Patent Citations (2)
Title |
---|
Fixed Point Quantization of Deep Convolutional Networks;Darryl D. Lin et.al;《arXiv:1511.06393v3 [cs.LG]》;20160602;第1-10页 * |
卷积神经网络的定点化研究;陈俊保 等;《信息技术》;20180731(第7期);第94-96页 * |
Also Published As
Publication number | Publication date |
---|---|
CN109359728A (zh) | 2019-02-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108701250B (zh) | 数据定点化方法和装置 | |
US10491239B1 (en) | Large-scale computations using an adaptive numerical format | |
WO2019238029A1 (zh) | 卷积神经网络系统和卷积神经网络量化的方法 | |
CN110874625B (zh) | 一种数据处理方法及装置 | |
CN111723901B (zh) | 神经网络模型的训练方法及装置 | |
JP2021072103A (ja) | 人工ニューラルネットワークの量子化方法とそのためのシステム及び人工ニューラルネットワーク装置 | |
CN109344893B (zh) | 一种基于移动终端的图像分类方法 | |
WO2021135715A1 (zh) | 一种图像压缩方法及装置 | |
CN111240746B (zh) | 一种浮点数据反量化及量化的方法和设备 | |
CN110717585A (zh) | 神经网络模型的训练方法、数据处理方法和相关产品 | |
WO2022021834A1 (zh) | 神经网络模型确定方法、装置、电子设备、介质及产品 | |
CN111967608A (zh) | 数据处理方法、装置、设备及存储介质 | |
CN112200296A (zh) | 网络模型量化方法、装置、存储介质及电子设备 | |
CN110874627A (zh) | 数据处理方法、数据处理装置及计算机可读介质 | |
Wu et al. | Phoenix: A low-precision floating-point quantization oriented architecture for convolutional neural networks | |
CN116884398B (zh) | 语音识别方法、装置、设备和介质 | |
CN109359728B (zh) | 计算神经网络压缩最佳定点位数的方法、存储介质和装置 | |
CN113780523A (zh) | 图像处理方法、装置、终端设备及存储介质 | |
CN112686365B (zh) | 运行神经网络模型的方法、装置和计算机设备 | |
CN114065913A (zh) | 模型量化方法、装置及终端设备 | |
CN111614358B (zh) | 基于分通道量化的特征提取方法、系统、设备及存储介质 | |
CN114222997A (zh) | 用于对神经网络进行后训练量化的方法和装置 | |
WO2016110125A1 (zh) | 高维向量的哈希方法、向量量化方法及装置 | |
CN113902928A (zh) | 图像特征的提取方法、装置及电子设备 | |
CN113760407A (zh) | 信息处理方法、装置、设备及存储介质 |
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 | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20190619 Address after: B203-205, Block B, Zhongguancun Development Building, 12 Information Road, Haidian District, Beijing, 100085 Applicant after: Deep thinking artificial intelligence robot technology (Beijing) Co., Ltd. Applicant after: Shanghai Shenxin Intelligent Technology Co., Ltd. Address before: 100084 B203, Zone B, Zhongguancun Development Building, 12 Shangdi Information Road, Haidian District, Beijing Applicant before: Deep thinking artificial intelligence robot technology (Beijing) Co., Ltd. |
|
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: B203-205, Block B, Zhongguancun Development Building, 12 Information Road, Haidian District, Beijing, 100085 Applicant after: IDEEPWISE ARTIFICIAL INTELLIGENCE ROBOT TECHNOLOGY (BEIJING) Co.,Ltd. Applicant after: Deep thinking of artificial intelligence technology (Shanghai) Co.,Ltd. Address before: B203-205, Block B, Zhongguancun Development Building, 12 Information Road, Haidian District, Beijing, 100085 Applicant before: IDEEPWISE ARTIFICIAL INTELLIGENCE ROBOT TECHNOLOGY (BEIJING) Co.,Ltd. Applicant before: Shanghai Shenxin Intelligent Technology Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |