CN112270405A - 基于范数的卷积神经网络模型的滤波器剪枝方法和*** - Google Patents
基于范数的卷积神经网络模型的滤波器剪枝方法和*** Download PDFInfo
- Publication number
- CN112270405A CN112270405A CN202011345927.0A CN202011345927A CN112270405A CN 112270405 A CN112270405 A CN 112270405A CN 202011345927 A CN202011345927 A CN 202011345927A CN 112270405 A CN112270405 A CN 112270405A
- Authority
- CN
- China
- Prior art keywords
- cluster
- filter
- pruning
- norm
- convolutional 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.)
- Pending
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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Description
Claims (8)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011345927.0A CN112270405A (zh) | 2020-11-26 | 2020-11-26 | 基于范数的卷积神经网络模型的滤波器剪枝方法和*** |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011345927.0A CN112270405A (zh) | 2020-11-26 | 2020-11-26 | 基于范数的卷积神经网络模型的滤波器剪枝方法和*** |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112270405A true CN112270405A (zh) | 2021-01-26 |
Family
ID=74339621
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011345927.0A Pending CN112270405A (zh) | 2020-11-26 | 2020-11-26 | 基于范数的卷积神经网络模型的滤波器剪枝方法和*** |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112270405A (zh) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113283473A (zh) * | 2021-04-20 | 2021-08-20 | 中国海洋大学 | 一种基于cnn特征映射剪枝的快速水下目标识别方法 |
CN113516638A (zh) * | 2021-06-25 | 2021-10-19 | 中南大学 | 一种神经网络内部特征重要性可视化分析及特征迁移方法 |
CN113657421A (zh) * | 2021-06-17 | 2021-11-16 | 中国科学院自动化研究所 | 卷积神经网络压缩方法和装置、图像分类方法和装置 |
CN113743591A (zh) * | 2021-09-14 | 2021-12-03 | 北京邮电大学 | 一种自动化剪枝卷积神经网络的方法及其*** |
-
2020
- 2020-11-26 CN CN202011345927.0A patent/CN112270405A/zh active Pending
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113283473A (zh) * | 2021-04-20 | 2021-08-20 | 中国海洋大学 | 一种基于cnn特征映射剪枝的快速水下目标识别方法 |
CN113283473B (zh) * | 2021-04-20 | 2023-10-13 | 中国海洋大学 | 一种基于cnn特征映射剪枝的快速水下目标识别方法 |
CN113657421A (zh) * | 2021-06-17 | 2021-11-16 | 中国科学院自动化研究所 | 卷积神经网络压缩方法和装置、图像分类方法和装置 |
CN113657421B (zh) * | 2021-06-17 | 2024-05-28 | 中国科学院自动化研究所 | 卷积神经网络压缩方法和装置、图像分类方法和装置 |
CN113516638A (zh) * | 2021-06-25 | 2021-10-19 | 中南大学 | 一种神经网络内部特征重要性可视化分析及特征迁移方法 |
CN113743591A (zh) * | 2021-09-14 | 2021-12-03 | 北京邮电大学 | 一种自动化剪枝卷积神经网络的方法及其*** |
CN113743591B (zh) * | 2021-09-14 | 2023-12-26 | 北京邮电大学 | 一种自动化剪枝卷积神经网络的方法及其*** |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112270405A (zh) | 基于范数的卷积神经网络模型的滤波器剪枝方法和*** | |
CN108764471B (zh) | 基于特征冗余分析的神经网络跨层剪枝方法 | |
CN109615014B (zh) | 一种基于kl散度优化的3d物体数据分类***与方法 | |
CN108288270B (zh) | 一种基于通道修剪与全卷积深度学习的目标检测方法 | |
CN106991047B (zh) | 一种用于对面向对象软件缺陷进行预测的方法及*** | |
CN111242180B (zh) | 一种基于轻量化卷积神经网络的图像识别方法及*** | |
CN112685504B (zh) | 一种面向生产过程的分布式迁移图学习方法 | |
CN113283473B (zh) | 一种基于cnn特征映射剪枝的快速水下目标识别方法 | |
CN113657421B (zh) | 卷积神经网络压缩方法和装置、图像分类方法和装置 | |
CN108280236A (zh) | 一种基于LargeVis的随机森林可视化数据分析方法 | |
CN115035418A (zh) | 一种基于改进DeepLabV3+网络的遥感图像语义分割方法及*** | |
CN113822419B (zh) | 一种基于结构信息的自监督图表示学习运行方法 | |
CN112288087A (zh) | 一种神经网络剪枝方法、装置、电子设备及存储介质 | |
Yue et al. | Face recognition based on histogram equalization and convolution neural network | |
CN111523483A (zh) | 中餐菜品图像识别方法及装置 | |
CN108875532A (zh) | 一种基于稀疏编码和长度后验概率的视频动作检测方法 | |
CN113554084A (zh) | 基于剪枝和轻量卷积的车辆再辨识模型压缩方法及*** | |
CN110991554B (zh) | 一种基于改进pca的深度网络图像分类方法 | |
CN115049941A (zh) | 一种改进的ShuffleNet卷积神经网络及其遥感图像的分类方法 | |
CN113177580A (zh) | 基于通道重要性剪枝与二值量化的图像分类*** | |
CN115908833A (zh) | 一种基于改进YOLOv3的轻量级垃圾检测方法 | |
CN108960326B (zh) | 一种基于深度学习框架的点云快速分割方法及其*** | |
CN114510871A (zh) | 基于思维进化和lstm的云服务器性能衰退预测方法 | |
CN114417095A (zh) | 一种数据集划分方法及装置 | |
CN112132207A (zh) | 基于多分支特征映射目标检测神经网络构建方法 |
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 | ||
CB03 | Change of inventor or designer information |
Inventor after: Li Kenli Inventor after: Ding Haotao Inventor after: Liu Chubo Inventor after: Xiao Guoqing Inventor after: Yang Wangdong Inventor after: Zhou Xu Inventor after: Tang Zhuo Inventor after: Li Keqin Inventor before: Liu Chubo Inventor before: Ding Haotao Inventor before: Li Kenli Inventor before: Xiao Guoqing Inventor before: Yang Wangdong Inventor before: Zhou Xu Inventor before: Tang Zhuo Inventor before: Li Keqin |
|
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210126 |