Data enhancement strategy generation method and device and data enhancement method and device

Abstract

The invention provides a data enhancement strategy generation method and device and a data enhancement method and device. The method comprises the following steps: obtaining training data and verification data; outputting a data enhancement strategy through a strategy generator, performing data enhancement processing on the training data through the data enhancement strategy, training a to-be-trained network by adopting the enhanced training data, verifying the trained network through verification data, and adjusting parameters in the strategy generator according to an obtained verification result; and circularly executing the steps until a preset condition is met, thereby obtaining a final data enhancement strategy. According to the method, a Bayesian optimization mode is introduced to search a data enhancement strategy; in the searching process, the strategy generator predicts the data enhancement strategy based on the historical verification result, then the parameters of the strategy generator are continuously adjusted in the subsequent verification process, and finally the optimal data enhancement strategy is obtained, so that the implementation difficulty of searching the optimal strategy is reduced, and the calculation cost is saved.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a method for generating a data enhancement strategy, a data enhancement method and a device. Background technique [0002] Deep learning tasks often require large amounts of data. In order to obtain these large amounts of data, some computer vision methods can be used to perform some transformations on the existing image data to obtain equivalent new data that is highly correlated with the original data. This method is called data enhancement. In related technologies, when selecting an enhancement strategy for image data, most of them use reinforcement learning to search for the optimal strategy, but it usually takes tens of thousands of iterations to converge and obtain the optimal result, which makes the implementation of this method difficult and computationally expensive. high. Contents of the invention [0003] The object of the present invention is to p...

AI Technical Summary

Problems solved by technology

In related technologies, when selecting an enhancement strategy for image data, most of them use reinforcement learning to search for the optimal strategy, but it usually takes tens of thousands of iterations to converge and obtain the optimal result, which makes the implementation of this method more difficult and computationally expensive. high

Images