Model training method and terminal equipment

Abstract

The invention relates to the technical field of computers, and provides a model training method and terminal equipment. The method comprises the steps of obtaining a to-be-trained model and training data; wherein the training data comprises a plurality of samples, and each sample corresponds to a probability value; selecting a plurality of samples from the training data according to the probability value of each sample to generate a training data set; training the to-be-trained model through the training data set, and obtaining an recognition result of the to-be-trained model for the trainingdata set; calculating a clustering effect evaluation value of the training data set according to the recognition result and the training data set; and adjusting the probability value corresponding toeach sample in the training data set according to the clustering effect evaluation value. According to the method, model training and training data screening are combined, so that the training efficiency of model training can be improved; in the training iteration process, the effect of difficult-to-recognize samples on model training can be enhanced, and then the robustness and accuracy of the trained model are improved.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a model training method and terminal equipment. Background technique [0002] Artificial intelligence technology needs to use a large amount of training data for model training. Taking artificial intelligence face recognition technology as an example, if you want to train a model with superior performance, you need millions of face pictures at every turn. A large number of face pictures requires a lot of manpower and material resources to manually collect and clean up the faces of different people. Due to factors such as human eye fatigue, there may be wrong pictures in a large number of manually collected pictures, resulting in many noisy pictures in the pictures in the training set. [0003] In addition, there are some face pictures in the training data, which may be difficult to recognize due to lighting, shooting angles, etc. However, in practical applications, f...

AI Technical Summary

Problems solved by technology

[0005] In view of this, the embodiment of the present invention provides model training and terminal equipment to solve the current problem of long training period and low efficiency of model training due to the presence of noise samples and difficult-to-recognize samples in the training data

Images