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

Abstract

The embodiment of the invention discloses a deep model training method and device, electronic equipment and a storage medium. The deep learning model training method includes: obtaining the n+1th first label information output by the first model, and the first model has undergone n rounds of training; and obtaining the n+1th second label information output by the second model labeling information, the second model has undergone n rounds of training; n is an integer greater than 1; based on the training data and the n+1th first labeling information, the n+1th training set of the second model is generated, And based on the training data and the n+1th second labeling information, generate the n+1th training set of the first model; input the n+1th training set of the second model into the described Two models, performing the n+1th round of training on the second model; inputting the n+1th training set of the first model into the first model, and performing the n+1th round on the first model train.

Description

technical field [0001] The present invention relates to the field of information technology, in particular to a deep model training method and device, electronic equipment and a storage medium. Background technique [0002] The deep learning model can have a certain classification or recognition ability after being trained by the training set. The training set generally includes: training data and labeled data of the training data. However, in general, labeling data requires manual labeling. On the one hand, manually labeling all the training data requires heavy workload and low efficiency, and there are human errors in the labeling process; on the other hand, if you need to achieve high-precision labeling, for example, in the image field, you need to achieve pixel-level Segmentation, purely manual labeling to achieve pixel-level segmentation is very difficult and the labeling accuracy is difficult to guarantee. [0003] Therefore, the training of deep learning models bas...

AI Technical Summary

Problems solved by technology

However, in general, labeling data requires manual labeling

On the one hand, manually labeling all the training data requires heavy workload and low efficiency, and there are human errors in the labeling process; on the other hand, if you need to achieve high-precision labeling, for example, in the image field, you need to achieve pixel-level Segmentation, purely manual labeling to achieve pixel-level segmentation is very difficult and the labeling accuracy is difficult to guarantee

[0003] Therefore, the training of deep learning models based on purely manually labeled training data will have low training efficiency, and the trained model will not meet expectations due to the low accuracy of the training data itself, resulting in the classification or recognition accuracy of the model.

Images