Iteration method and device of kernel model

Abstract

The invention provides an iteration method and device for a kernel model, and the method comprises the steps: carrying out the desensitization of received data, and extracting and screening feature data from the desensitized data; selecting hyper-parameters from the feature data according to the state of the nuclear body model, and training the nuclear body model; and evaluating the trained nuclear body model, and after the evaluation is qualified, putting the iterated nuclear body model on line. The problem that the performance of the deep learning algorithm is influenced by data change because the distribution of the test data and the distribution of the training data are changed due to different time is solved; meanwhile, the problem that the performance of the deep learning algorithm is affected by data change due to the fact that the distribution of test data and the distribution of training data change due to different scenes is also solved; according to the method provided by the invention, the updated model can be adaptive to each scene, the extreme performance of the algorithm is brought into play, and the nuclear body verification accuracy of the algorithm is improved.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to an iterative method and device for a core body model. Background technique [0002] At present, the core body system, such as the commonly used face recognition system, includes multiple modules such as face detection, face calibration, and face comparison. In these modules, almost all algorithms are implemented by deep learning models. Deep learning is a data-driven learning algorithm, that is, when the distribution of the test data is close to the distribution of the training data, the performance of the deep learning algorithm will be better. [0003] In practical applications, with the different application scenarios of the algorithm, the distribution of the test data will form a large or small gap with the distribution of the training data, which will affect the actual performance of the algorithm. On the other hand, as time goes by, even in the same scene, the distribut...

AI Technical Summary

Problems solved by technology

[0004] An object of the present invention is to provide an iterative method and device for a core body model to solve the existing problem of inaccurate model verification due to the gap between the distribution of test data and the distribution of training data due to different scenarios or time

Images