GAN Evaluation Method Based on Remote Sensing Image Information

To address the problem of poor applicability of the existing generative adversarial network (GAN) evaluation system, this paper introduces the remote sensing image information quantity calculation system into the generative adversarial network evaluation indicator system, proposes an end-to-end GAN evaluation method based on the single-pixel image information quantity indicator, and uses EDS, ENDS, and InfoDS to evaluate the stability of the generator training process, mode collapse, diversity generation, and training failure problem is effectively monitored, which independent of loss function, learning rate.