Unlock instant, AI-driven research and patent intelligence for your innovation.

Neural network training method and device, electronic equipment and storage medium

A neural network training and neural network technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve the problems of reducing the efficiency of neural network tailoring, consuming time and computing resources, etc.

Pending Publication Date: 2021-06-29
SENSETIME GRP LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The above-mentioned neural network compression or neural network tailoring methods have the following problems: a large amount of time and computing resources are consumed when training a large neural network. A round of channel pruning, especially when the pruning rate of the channel is high, requires Duolun’s channel pruning, which not only consumes a lot of time and computing resources, but also reduces the efficiency of neural network pruning

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
  • Neural network training method and device, electronic equipment and storage medium
  • Neural network training method and device, electronic equipment and storage medium
  • Neural network training method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] In order to make the purpose, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only It is a part of the embodiments of the present disclosure, but not all of them. The components of the disclosed embodiments generally described and illustrated in the figures herein may be arranged and designed in a variety of different configurations. Accordingly, the following detailed description of the embodiments of the present disclosure provided in the accompanying drawings is not intended to limit the scope of the claimed disclosure, but merely represents selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those ski...

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 provides a neural network training method and device, an intelligent driving method and equipment, electronic equipment and a storage medium. According to the method, the to-be-clipped neural network is excessively clipped to obtain the over-clipped neural network with the network scale smaller than that of the target neural network, and then the target neural network is obtained by adding the channels in the second network layer having great influence on the detection precision in the over-clipped neural network, so that a large neural network does not need to be trained. Time and computing resources are saved. And meanwhile, multiple rounds of channel clipping are not needed, the target neural network can be obtained through single iteration only by adding a channel in the second network layer with large influence on the detection precision, time and computing resources are further saved, and the clipping efficiency of the neural network is improved.

Description

technical field [0001] The present disclosure relates to the technical fields of automatic driving and neural network, and in particular, relates to a neural network training method, device, intelligent driving method, equipment, electronic equipment, and computer-readable storage medium. Background technique [0002] In autonomous driving, neural network compression or neural network pruning techniques have become more and more important due to the limited storage and computing resources on the vehicle. The current compression algorithm generally trains a large neural network with a large amount of parameters and takes a long time, and then tailors the large neural network to generate a neural network that meets the requirements of detection accuracy and running time and can be deployed on vehicle equipment. [0003] The above-mentioned neural network compression or neural network tailoring methods have the following problems: a large amount of time and computing resources ...

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
IPC IPC(8): G06N3/04G06N3/08
CPCG06N3/082G06N3/045
Inventor 侯跃南王哲付万增石建萍
Owner SENSETIME GRP LTD