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

Automatic model training method and device, equipment and medium

A model training and model technology, applied in the computer field, to achieve the effect of reducing repetitive work, easy to use, and standardizing the model training process

Inactive Publication Date: 2019-08-16
MEGVII BEIJINGTECH CO LTD
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the shortcomings of the existing methods, this application proposes an automated model training method, device, equipment and computer-readable storage medium to solve the problem of how to realize the convenience of using components and reduce the repetitive work of model training

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
  • Automatic model training method and device, equipment and medium
  • Automatic model training method and device, equipment and medium
  • Automatic model training method and device, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] An automated model training method is provided in the embodiment of the present application, and the schematic flow chart of the method is as follows figure 1 As shown, the method includes:

[0034] S101. Acquire model training parameters, where the model training parameters include a data component, a model component, and a training component.

[0035] S102. Construct at least one deep learning model according to the model components included in the model training parameters.

[0036] S103. Automatically train any deep learning model according to the data component and the training component included in the model training parameters.

[0037] In the embodiment of the present application, the model training parameters are obtained, and the model training parameters include data components, model components and training components; according to the model components included in the model training parameters, at least one deep learning model is constructed; according to t...

Embodiment 2

[0082] Based on the same inventive concept, the embodiment of the present application also provides an automatic model training device, the structural diagram of which is shown in Figure 5 As shown, the automated model training device 50 includes a first processing module 501 , a second processing module 502 and a third processing module 503 .

[0083] The first processing module 501 is configured to acquire model training parameters, and the model training parameters include data components, model components and training components.

[0084] The second processing module 502 is configured to construct at least one deep learning model according to the model components included in the model training parameters.

[0085] The third processing module 503 is configured to perform automatic training on any deep learning model according to the data components and training components included in the model training parameters.

[0086] Optionally, the third processing module 503 is sp...

Embodiment 3

[0097] Based on the same inventive concept, the embodiment of the present application also provides an electronic device, the schematic structural diagram of which is as follows Image 6 As shown, the electronic device 6000 includes at least one processor 6001, a memory 6002 and a bus 6003, and at least one processor 6001 is electrically connected to the storage 6002; the memory 6002 is configured to store at least one computer-executable instruction, and the processor 6001 It is configured to execute the at least one computer-executable instruction, so as to execute the steps of any automated model training method provided in any one of the first embodiments of the present application or any optional implementation.

[0098] Further, the processor 6001 may be FPGA (Field-Programmable Gate Array, field programmable gate array) or other devices with logic processing capabilities, such as MCU (Microcontroller Unit, micro control unit), CPU (Central Process Unit, central processin...

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 an automatic model training method and device, equipment and a computer readable storage medium, the method comprises: acquiring model training parameters, wherein the model training parameters comprise a data component, a model component and a training component; constructing at least one deep learning model according to model components included in the model training parameters; and according to data components and training components included in the model training parameters, carrying out automatic training on any deep learning model. According to the method, the assembly is convenient to use, repeated work of model training is reduced, assembly disassembling of the model training process is achieved, the flexibility is higher, the model trainingprocess is standardized, and the model precision is improved.

Description

technical field [0001] The present application relates to the field of computer technology, and in particular, the present application relates to an automatic model training method, device, equipment and computer-readable storage medium. Background technique [0002] To use deep learning models to classify images or solve simple regression problems, different components need to be selected according to different project requirements, such as model structures with different calculation and parameter quantities, data enhancement methods, model training parameters, etc. [0003] The current problems are that the deep learning model cannot be reused under different tasks. The training of the deep learning model mainly designs the appropriate network structure according to the specific task, and adjusts various hyperparameters, data processing methods, etc. For basic tasks, especially During the early iterations of the model, the adjustable components were largely fixed. The log...

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): G06K9/62
CPCG06F18/24G06F18/214
Inventor 王彤
Owner MEGVII BEIJINGTECH 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