Neural network model input channel integration method for transfer learning

A neural network model and input channel technology, which is applied in the field of neural network model input channel integration, can solve the problems of occupying memory space, increasing the calculation amount of neural network, and increasing the processing time of copy channel, so as to reduce the amount of calculation, reduce the pressure, shorten the The effect of processing time

Pending Publication Date: 2020-09-11
BEIJING AEROSPACE AUTOMATIC CONTROL RES INST
View PDF6 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the currently commonly used visible light, infrared or radar SAR scene data are mostly single-channel, which cannot meet the input requirements of neural network models.
[0003] In practical application, a simple and feasible method is to copy two channels of single-channel image data and splicing in the channel dimension to generate three-channel data. However, after testing, this method has inevitable defects: in the embe

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 model input channel integration method for transfer learning
  • Neural network model input channel integration method for transfer learning
  • Neural network model input channel integration method for transfer learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The invention relates to a neural network model input channel integration method for migration learning, which is suitable for various general target detection and recognition algorithms and network frameworks based on convolutional neural networks, and realizes data exchange between heterogeneous training data and actual test data Uniform format.

[0039] A neural network model input channel integration method for transfer learning, the steps are as follows:

[0040] Step 1: Modify the data input layer description in the network model description file, delete the original data input layer description, and add the data input layer description based on the image data list; and rename the first convolutional layer to be modified;

[0041] The present invention is not limited to a specific neural network framework, and can be implemented for mainstream frameworks tensorflow, caffe, and pytorch. The following is a specific description, and the caffe framework is temporarily...

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 discloses a neural network model input channel integration method for transfer learning, and the method comprises: firstly modifying a data input layer description in a network model description file, deleting an original data input layer description, adding a data input layer description based on an image data list, and renaming a to-be-modified first convolution layer; reading a neural network model weight file, and modifying the neural network model weight file, so that the corresponding neural network model only needs single-channel data as input; and finally, carrying out real-time target detection, identification and test on the single-channel image data. According to the invention, network model weight files trained by three-channel training sample data are analyzed and integrated; a network model weight file input by a single channel is formed and directly deployed on an embedded platform, channel copying operation is not needed, redundant memory space does not need to be occupied, the calculation amount of a neural network is reduced, the pressure on information processing resources is reduced, and real-time target detection and recognition can be directly completed on single-channel data.

Description

technical field [0001] The invention relates to a neural network model input channel integration method for transfer learning, which belongs to the field of neural network intelligent target detection and recognition. Background technique [0002] The target detection and recognition algorithm based on convolutional neural network needs a large amount of training sample data in the process of model weight training. For some specific application environments, the amount of image data containing valid targets is too small to support algorithm model training, and it is necessary to use public databases for pre-training and other operations. However, most of the public databases are naturally collected three-channel color images, so the input of the trained model is also required to be three-channel data. However, most of the currently used visible light, infrared or radar SAR scene data are single-channel, which cannot meet the input requirements of neural network models. [...

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): G06N3/04G06N3/08G06K9/62
CPCG06N3/08G06V2201/07G06N3/045G06F18/214
Inventor 靳松直周斌张辉郝梦茜刘严羊硕丛龙剑韦海萍张聪郑文娟王浩刘燕欣高琪
Owner BEIJING AEROSPACE AUTOMATIC CONTROL RES INST
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
Try Eureka
PatSnap group products