Classification model training method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a classification model training method. The method comprises steps that the gradient contribution corresponding to each sample in the current batch of data is obtained in a training process of a classification model; samples with the gradient contribution larger than or equal to a preset gradient contribution threshold value in the current batch of data serve as first difficult samples and are added into a difficult sample set, the difficult sample set comprises second difficult samples, and the second difficult samples are samples with the gradient contribution larger than or equal to the preset gradient contribution threshold value in the non-current batch of data; and a third difficult sample is selected from the difficult sample set according to a preset screening rule, and the classification model is trained according to the third difficult sample. According to the method, difficult sample mining is carried out on the current batch of data and the non-current batch of data, and the third difficult sample is screened out from the first difficult sample and the second difficult sample, so the screening range of the third difficult sample is enlarged, more representative difficult samples can be obtained to train the classification model, and classification recognition accuracy of the classification model is improved.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to a training method, device, electronic equipment and storage medium for a classification model. Background technique [0002] In the training process of the classification model, it is necessary to use sample data as input, so that the classification model can learn the classification of the sample data under supervision. Sample data can be divided into simple samples and difficult samples. Simple samples and difficult samples are defined relative to the classification model. The classification model can accurately classify and identify samples as simple samples, and the classification model cannot accurately classify and identify samples as difficult samples. In order to improve the accuracy of the classification model, during the training process of the classification model, the method of mining difficult samples is usually used to train the model, so that the model only u...

AI Technical Summary

Problems solved by technology

However, in the actual model training task, difficult sample mining is limited to the samples in the current batch data batch size, and the multi-machine distributed training task adopts the data parallel training mode to be carried out under a single trainer worker. Hard sample mining will not be able to take advantage of the large batch data brought about by distributed training. Therefore, the existing difficult sample mining method is to mine in a small range of batch data. The mining range of difficult samples is small, making classification The classification and recognition accuracy of the model is not high

Images