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

Model training method and device and computer equipment

A model training and model technology, applied in the computer field, can solve the problem that the one-way building model cannot meet the needs of the model's use effect, and achieve the effect of saving training costs, good training effect, and improved prediction effect.

Active Publication Date: 2020-07-24
深圳市友杰智新科技有限公司
View PDF9 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The main purpose of this application is to provide a model training method, aiming to solve the technical problem that the existing one-way construction model cannot meet the requirements of the model use effect

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
  • Model training method and device and computer equipment
  • Model training method and device and computer equipment
  • Model training method and device and computer equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049]In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

[0050] refer to figure 1 , the model training method of an embodiment of the present application, the model includes a first Siamese network composed of a first encoder and a second encoder, and the method includes:

[0051] S1: Obtain a first high-dimensional vector output by the first encoder after processing the first data, and a second high-dimensional vector output by the second encoder after processing the second data;

[0052] S2: Train the first twin network with the first loss function, and when the first loss function reaches the minimum value, the first twin net...

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 model training method, a model comprises a first twin network composed of a first encoder and a second encoder, and the method comprises the steps: obtaining a first high-dimensional vector outputted by the first encoder after processing first data, and a second high-dimensional vector outputted by the second encoder after processing second data; training the first twin network through a first loss function until the first loss function reaches a minimum value, and converging the training of the first twin network; obtaining a first parameter set corresponding to thefirst encoder and a second parameter set corresponding to the second encoder when the first twin network training converges; forming a second twin network by the first encoder and the first recovery network under the first parameter set, and forming a third twin network by the second encoder and the second recovery network under the second parameter set; and respectively training the second twin network and the third twin network to converge through the second loss function to obtain a network model system for executing the dual task. Model construction and training cost is saved, and model training is improved.

Description

technical field [0001] This application relates to the field of computers, in particular to a model training method, device and computer equipment. Background technique [0002] In deep learning, there are many Sequence-2-Sequence prediction tasks with a dual relationship, such as speech recognition and speech synthesis, machine translation (Chinese-to-English and English-to-Chinese), text-to-image and picture-to-speech, text summarization and text generation, etc. . Due to the diversity of sequences, generally larger models and large-scale training data are required to achieve satisfactory results. In practice, the construction of the above task models is one-way. For example, speech recognition can only process the reasoning process from voice data to text, and speech synthesis can only process the reasoning process from text data to audio; similarly, the Chinese-to-English model can only process Chinese is translated into English, and the English-to-Chinese model can on...

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): G06F40/58G06N3/08
CPCG06N3/08
Inventor 徐泓洋太荣鹏温平
Owner 深圳市友杰智新科技有限公司
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