Data processing model generation method and device, medium and electronic equipment
A technology for data processing and model generation, applied in neural learning methods, biological neural network models, design optimization/simulation, etc., can solve problems such as low efficiency and weak model compression flexibility, and achieve lower requirements, lower acquisition difficulty, and reduced The effect of data processing volume
Pending Publication Date: 2021-12-28
TENCENT TECH (SHENZHEN) CO LTD
View PDF0 Cites 4 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The purpose of this application is to provide a data processing model generation method, device, readable medium and electronic equipment to solve the problem of weak model compression flexibility and low efficiency in related technologies
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0057] Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be thorough and complete, and will fully convey the concepts of example embodiments to those skilled in the art.
[0058] Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided in order to give a thorough understanding of the embodiments of the application. However, those skilled in the art will appreciate that the technical solutions of the present application may be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be employed. In other instances, well-known methods,...
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
Login to View More Abstract
The invention discloses a data processing model generation method and device, a readable medium and electronic equipment, and the method comprises the steps: carrying out the data enhancement processing of sample data to obtain a first training sample and a second training sample corresponding to the sample data; performing feature extraction on the first training sample through a teacher model to obtain teacher sample features; taking the teacher sample features as training targets of a student model, and training the student model through a second training sample; and after a training ending condition is satisfied, generating a target data processing model according to the student model obtained by training. According to the technical scheme provided by the embodiment of the invention, the requirement for sample data and the data processing amount in the training process are greatly reduced, and the training efficiency of the student model is improved. Meanwhile, limited sample data is expanded into more training samples, so the acquisition difficulty of the sample data is reduced, and the flexibility of model learning is improved.
Description
technical field [0001] The application belongs to the technical field of computer and image processing, and in particular relates to a data processing model generation method, device, readable medium and electronic equipment. Background technique [0002] In recent years, with the rapid development of deep learning, deep neural networks have achieved remarkable results in many application fields. Usually, under high computational load, the learning ability of deep neural network continues to improve with the increase of network layer depth, so deep neural network performs very well on large data sets. However, deep learning cannot be effectively applied to lightweight mobile portable devices due to its characteristics such as heavy computation, high storage cost, and complex models. Therefore, model compression methods that reduce the size of deep learning models while maintaining their performance have become a hot research topic. However, the model compression method in ...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06F30/27G06K9/62G06N3/08
CPCG06F30/27G06N3/08G06F18/214
Inventor 顾金东刘威
Owner TENCENT TECH (SHENZHEN) CO LTD