Method for compressing power transmission network picture in complex environment based on generative adversarial network

The invention discloses a method for compressing a power transmission network picture in a complex environment based on a generative adversarial network, and the method comprises the steps: inputtinga picture into a model trained through the generative adversarial network, obtaining a feature code of the picture, transmitting and storing the feature code, and restoring the feature code into the picture. According to the method, normalization processing is carried out by using Instance _ norm after each convolution, and the mean value and variance of each layer of feature map are solved, so that the model can better learn the features of the pictures in the power transmission network; the feature codes of the pictures of the power transmission network are obtained through the trained model, and the feature codes are transmitted and stored, so that the data transmission time is saved, the storage cost is reduced, and the transmission bandwidth cost is reduced; and through a plurality ofDenseBlock and Transition