Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Intelligent pruning method and system for deep network compression

A deep network and pruning technology, applied in the field of intelligent pruning methods and systems, can solve the problems of security check channel congestion, limited computing resources, complex network structure, etc., to avoid congestion, less computing resources, and avoid computing redundancy. Effect

Pending Publication Date: 2022-07-29
XIDIAN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, the network structure of the convolutional neural network is complex and cannot meet the needs of fast and real-time applications, which will lead to congestion of the security inspection channel during the security inspection process. In the actual application scenarios identified, computing resources are limited due to space and cost constraints, and it cannot be applied in real life on a large scale

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Intelligent pruning method and system for deep network compression
  • Intelligent pruning method and system for deep network compression
  • Intelligent pruning method and system for deep network compression

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] Convolutional neural network is a representative neural network in the field of deep learning technology, and it is also an important basis for the breakthrough achievements of deep learning technology in the field of computer vision. As the complexity of the task increases, the number of layers of the convolutional neural network is also increasing, and the scale of the model is also increasing. Today’s mainstream deep neural networks often have millions of parameters, making model training exponentially more difficult. In order to deploy trained deep convolutional neural networks on IoT and edge devices and achieve real-time fast inference, it is necessary to compress these deep convolutional neural networks to effectively reduce the memory space occupied by the model and the requirements for model inference. energy consumption.

[0046] Please refer to figure 1 and figure 2 , figure 1 is a schematic diagram of an intelligent pruning method for deep network compr...

Embodiment 2

[0088] This embodiment illustrates the effects of the intelligent pruning method and system for deep network compression of the present invention through a specific simulation experiment.

[0089] 1. Simulation conditions

[0090] In this example, the CPU is configured as Intel(R) Core(TM) i7-9700K CPU@3.60GHz, the memory is 32G, the GPU is a single-card NVIDIA GeForce RTX 2070 video memory, the CUDA version is 11.3, and the Windows 10 operating system is used on a PC. , using the Python language to complete the simulation experiment.

[0091] 2. Content of the simulation experiment

[0092] The data used in this embodiment is a total of 60,000 three-channel color images in 10 different categories of CIFAR10. The training data for each category is 5,000 images, and the test data is 1,000 images. When evaluating the importance of the filter, the number of divided intervals is N=10, the pruning ratio is T=0.6, the training optimizer uses mini-batch SGD, adds momentum and weigh...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to an intelligent pruning method and system for deep network compression. The method comprises the following steps: acquiring a training sample set and an untrained to-be-compressed convolutional neural network; training the convolutional neural network by using the training sample set according to the sleep and waking mechanism of the neurons, and updating the information entropy of each filter in each convolutional layer in the convolutional neural network in the training process to obtain the trained convolutional neural network; and performing pruning processing on the filter of each convolutional layer according to the information entropy sequence of the filter of each convolutional layer in the trained convolutional neural network and a preset pruning proportion to obtain a trained and compressed compressed convolutional neural network. The compressed convolutional neural network obtained through the method can avoid operation redundancy in the security check image classification process, operation time is saved, and the compressed convolutional neural network can run on a platform with limited computing resources.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence, and in particular relates to an intelligent pruning method and system for deep network compression. Background technique [0002] With the rapid economic and social development, the current population mobility in my country has greatly increased. In order to maintain public safety, security checks are required in public places such as airports, railway stations, bus stations, and subway entrances to ensure people's travel safety. [0003] At present, the common security inspection equipment is the X-ray security inspection machine. During the use of the X-ray security inspection machine, the staff needs to carefully check the X-ray baggage image to determine whether it contains dangerous goods. The device has a low degree of intelligence and the cost of manual inspection. higher, and misjudgment and omission may also occur. [0004] With the rapid development of artificial intell...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/08G06N3/063G06N3/04
CPCG06N3/082G06N3/063G06N3/045
Inventor 王颖陈怡桦李洁王斌胡留成马浩中张建龙
Owner XIDIAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com