A training sample data expansion method and device based on a variational auto-encoder

Abstract

The embodiment of the invention provides a training sample data expansion method and device based on a variational auto-encoder, and relates to the technical field of big data. The method comprises the steps of obtaining an original sample; inputting the original sample into the encoder of the variational autoencoder, wherein the encoder of the variational autoencoder comprises two neural networks, the two neural networks output Mu and sigma respectively, and Mu and sigma are both functions of the original sample; according to the square of the Mu and sigma, namely sigma 2, generating a randomnumber of corresponding Gaussian distribution; randomly sampling the standard normal distribution to obtain a sampling value epsilon, and determining a sampling variable Z according to the sampling value epsilon and the random number of the Gaussian distribution; and inputting the sampling variable Z into a decoder of the variational autoencoder, decoding the sampling variable Z by the decoder ofthe variational autoencoder, and then outputting similar samples of the original samples, and taking the similar samples as extended samples. Therefore, the technical scheme provided by the embodiment of the invention can solve the problems that the time and labor are wasted and the efficiency is low when sample data is manually expanded in the prior art.

Description

【Technical field】 [0001] The invention relates to the field of big data technology, in particular to a method and device for expanding training sample data based on a variational autoencoder. 【Background technique】 [0002] With the development of computer application technology, deep learning technology has become more and more mature and has been widely used. Classification model training based on deep learning can provide automatic recognition function for input data. [0003] Using the method of deep learning to train the classification model is more efficient, but if the number of samples in the classification model is unbalanced or the number of samples is small, the classification effect of the model trained by deep learning will be reduced. Therefore, before training the classification model, a large amount of sample data needs to be provided. When the amount of sample data required is large, manually expanding the sample data is time-consuming, laborious, and ineffi...

AI Technical Summary

Problems solved by technology

[0004] In view of this, the embodiment of the present invention provides a training sample data expansion method and device based on a variational autoencoder to solve the time-consuming and labor-intensive and low-efficiency problems of manual expansion of sample data in the prior art

Images