Machine learning model training method and device and expression image classification method and device
A technology of machine learning model and training method, applied in the field of machine learning, can solve the problems of low training efficiency of machine learning models, achieve the effect of improving classification efficiency and accuracy, and improving training efficiency
Active Publication Date: 2018-07-20
TENCENT TECH (SHENZHEN) CO LTD
View PDF4 Cites 24 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] Based on this, it is necessary to provide a machine learning model training method and device, expression image classification method and device for the problem of low training efficiency of traditional machine learning models
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
[0035] In order to make the technical solutions and advantages of the present invention clearer, the present invention 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 invention, not to limit the present invention.
[0036] figure 1 It is an application environment diagram of a machine learning model training method and / or an expression image classification method in an embodiment. Such as figure 1 As shown, the machine learning model training method and / or expression image classification method is applied to a computer device. The computer device may be a terminal or a server. The terminal may be a desktop device or a mobile terminal. A server can be a stand-alone physical server, a cluster of physical servers, or a virtual server. Wherein, the computer device includes a processor connected through a system bus,...
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 relates to a machine learning model training method and device. The method comprises that a machine learning model provided with model parameters and obtained by training according to ageneral image training set are obtained; a sample of a special-purposed image and a corresponding classification label are determined; the sample of the special-purposed image is input to the machinelearning model to obtain an intermediate classification result; according to the intermediate classification result and difference of the intermediate classification result from the classification label, the model parameters of the machine learning model are adjusted, training is continued, and training is not ended unless a training stop condition is satisfied. Thus, the training efficiency of the machine learning model is improved.
Description
technical field [0001] The invention relates to the field of machine learning, in particular to a machine learning model training method and device, and an expression image classification method and device. Background technique [0002] At present, with the development of terminal storage technology and network technology, image-based interaction becomes easier and more and more users choose to use images for interaction, resulting in an increasing number of images used for interaction. Appropriate classification of images plays a very important role in user personalized recommendation and user portrait construction. Currently, trained machine learning models are available for image classification. The traditional machine learning model training method usually uses a large amount of training data to train the machine learning model, so that the model learns classification rules to improve the classification accuracy of the model. [0003] However, based on the traditional ...
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): G06N99/00G06K9/62G06K9/00G06V10/764G06V10/774
CPCG06N20/00G06V40/175G06V40/172G06F18/214G06N3/08G06V20/35G06V10/82G06V10/764G06V10/774G06N7/01G06N3/045G06F18/2155G06F18/2415G06N3/096
Inventor 刘龙坡万伟陈谦
Owner TENCENT TECH (SHENZHEN) CO LTD