Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Screening method and device for training models in training model group and electronic equipment

A technology for training models and screening methods, which is applied in the field of image processing, and can solve problems such as long and complex, affecting the practical research of technology, and inconvenient deployment of target recognition

Pending Publication Date: 2022-02-25
SUZHOU LANGCHAO INTELLIGENT TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the process of manual screening and parameter adjustment based on the established mathematical model and output results is often long and complicated, and the final model and parameters may not be optimal; when replacing the iterative training model, it is necessary to Adjust the confidence parameter group according to the target discovery rate and precision rate balance
If there are many variables that need to be adjusted, then there are more possible combinations of adjustments. This work is often not competent for non-professionals, which brings great inconvenience to the deployment of target recognition in engineering applications and seriously affects the practicality of the technology. chemical research

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
  • Screening method and device for training models in training model group and electronic equipment
  • Screening method and device for training models in training model group and electronic equipment
  • Screening method and device for training models in training model group and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] Embodiment 1 of the present invention provides a method for screening training models in a training model group. figure 1 It is a schematic flow chart of the training model screening method in the training model group in Example 1 of the present invention, as figure 1 As shown, the screening method of the training model in the training model group in Embodiment 1 of the present invention is specifically a method for determining the optimal solution of the training model group, comprising the following steps:

[0031] S101: Initialize the particle vector of each particle in the particle swarm.

[0032]As a specific implementation manner, the particle vector includes the number of iterations of the training model and the confidence levels of various objects in the training model.

[0033] For example, the particle vector of a particle in the particle swarm is expressed as X={x 0 ,x 1 ,x 2 ,...x n}. where x 0 is the number of training model iterations, x i is the c...

Embodiment 2

[0070] Corresponding to Embodiment 1 of the present invention, Embodiment 2 of the present invention provides a screening device for training models in a training model group, Figure 6 It is a schematic structural diagram of the training model screening method device in the training model group in Example 2 of the present invention, as Figure 6 As shown, the device for determining the optimal solution of the training model group in Embodiment 2 of the present invention includes an initialization module 20 and a screening module 21 .

[0071] Specifically, the initialization module 20 is used to initialize the particle vector of each particle in the particle swarm;

[0072] The screening module 21 is configured to input the detection samples and the particle vector of each particle into the training model group and use the particle swarm optimization algorithm to screen out the optimal solution of the training model group.

[0073] For details of the above electronic equipme...

Embodiment 3

[0078] An embodiment of the present invention also provides an electronic device, which includes a processor and a memory, where the processor and the memory can be connected through a bus or in other ways.

[0079] The processor may be a central processing unit (Central Processing Unit, CPU). The processor can also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application-specific integrated circuits (Application Specific Integrated Circuit, ASIC), field-programmable gate array (Field-Programmable Gate Array, FPGA) or other Chips such as programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or combinations of the above-mentioned types of chips.

[0080] As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs, non-transitory computer-executable programs and modules, such as the program corresponding to the method for de...

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 embodiment of the invention provides a screening method and device for training models in a training model group and electronic equipment. The screening method for the training models in the training model group comprises the steps of initializing a particle vector of each particle in a particle swarm; inputting a detection sample and the particle vector of each particle into a training model group, and screening out an optimal solution of the training model group by using a particle swarm algorithm. Therefore, the particle swarm optimization algorithm can be used for automatic optimization, and compared with manual optimization, the particle swarm optimization algorithm is faster and more accurate.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method, device and electronic equipment for screening training models in a training model group. Background technique [0002] Object detection has been an enduring research direction in the field of computer vision. Target detection is also a subjective process, which is quite simple for humans. Children who have not received any training can easily locate the target object by observing different colors, regions and other features in the picture, but the computer receives the RGB values ​​of these pictures. The pixel matrix will not directly obtain the abstract concept of the target (such as pedestrians, vehicles, etc.), let alone locate its position. Researchers have explored a solution to these relatively subjective problems. This solution is to design a method for computers to learn from massive experiences, and to fit things by building a hierarchical structure, ...

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): G06V10/774G06V10/776G06K9/62G06N3/04G06N3/08G06N3/12
CPCG06N3/086G06N3/126G06N3/045G06F18/217G06F18/214
Inventor 韩春超
Owner SUZHOU LANGCHAO INTELLIGENT TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap 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