A model processing method, device and storage medium
A model processing and model technology, applied in neural learning methods, biological neural network models, character and pattern recognition, etc., can solve problems affecting the accuracy of the model, and achieve the effect of improving accuracy and better recognition results
Active Publication Date: 2021-07-09
MIGU CO LTD +1
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] In view of this, the embodiment of the present invention expects to provide a model processing method, device and storage medium, which can overcome the problem that the accuracy of the model is affected by the difference in the feature space between the source library and the target library
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
[0029] In order to understand the characteristics and technical contents of the embodiments of the present invention in more detail, the implementation of the embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. The attached drawings are only for reference and description, and are not intended to limit the present invention.
[0030] figure 1 A kind of model processing method provided for the embodiment of the present invention; figure 1 As shown, the implementation process of the model processing method in the embodiment of the present invention may include the following steps:
[0031] Step 101: Extract first object features from the source database and extract second object features from the target database respectively, wherein the first object features and the second object features are sample sets in their respective databases.
[0032] In some embodiments, the first object features are extracted from the ...
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 present invention provides a model processing method, including: respectively extracting first object features from a source library and extracting second object features from a target library, wherein the first object features and the second object features are respectively Sample collections in the respective databases; respectively mapping the first object feature and the second object feature to the same feature space, and correspondingly obtaining the mapped first object feature and the mapped second object feature; according to the mapping After the first object feature after the mapping and the second object feature after the mapping, determine the transformation matrix when the difference between the source library and the target library meets the preset minimum difference condition; through the transformation matrix, the converting the mapped first object features to obtain third object features; applying the third object features and corresponding labels to a model for classifying samples in the target library. The invention also provides a model processing device and a storage medium.
Description
technical field [0001] The invention relates to electric digital data processing technology, in particular to a model processing method, device and storage medium. Background technique [0002] With the advent of the era of big data, people can obtain large amounts of data more easily. In addition, due to the continuous development of the field of machine learning, how to make computers have the ability to draw inferences from one instance and how to make large amounts of data play a better role, these problems have become It is very practical and valuable. In order to solve these problems, transfer learning has been proposed and has attracted more and more attention. [0003] There is an important assumption in conventional machine learning that the samples of the source library and the samples of the target library must have the same distribution or come from the same feature space. However, in real life, this assumption is difficult to achieve; specifically , for a class...
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 Patents(China)
IPC IPC(8): G06K9/62G06N3/08
CPCG06N3/08G06F18/214
Inventor 徐嵚嵛李琳周效军崔兴宇
Owner MIGU CO LTD