Multi-feature-learning-based adversarial network training method

Abstract

The invention, which belongs to the field of the deep learning neural network, discloses a multi-feature-learning-based adversarial network training method. The method comprises the following steps: S1, constructing a deep convolutional generative adversarial network (DCGAN) model; S2, constructing a plurality of convolution kernels for a determination device; S3, initializing random noises and inputting the processed noises into a generator; S4, with the plurality of constructed convolution kernels with different sizes, carrying out conversion processing on all images received by the determination device to obtain a plurality of characteristic patterns; and S5, outputting a mean value of loss functions of the plurality of characteristic patterns into the generator for continuous training.According to the method disclosed by the invention, the training method after picture receiving by the determination device is changed and thus the convolution process of the determination device iscarried out in parallel, so that a plurality of characteristics of the images generated by the generator are learned simultaneously and several kinds of characteristics in a data set are learned rapidly and thus images matching the characteristics of the data set are generated efficiently.

Description

technical field [0001] The invention relates to the technical field of deep learning neural network, in particular to a multi-feature learning confrontation network training method. Background technique [0002] Generative Adversarial Network (GAN for short) is a deep learning framework proposed by Goodfellow in 2014. It is based on the idea of ​​"game theory" and constructs two models, the generator and the discriminator. The former The image is generated by inputting (0, 1) uniform noise or Gaussian random noise, which discriminates the input image to determine whether it is an image from the dataset or an image produced by the generator. [0003] In the traditional confrontational network model, the discriminator often analyzes the features of the image generated by the generator through the operation of layer-by-layer convolution, and learns a new feature. It often needs to learn an old feature after the end. to proceed. In this case, the efficiency of network learning...

AI Technical Summary

Problems solved by technology

In this case, the efficiency of network learning and training is relatively low

Images