1Assistant Professor, Department of Information Technology, Maharaja Surajmal Institute of Technology, New Delhi, Email: joy.arora@gmail.com
2Student, Department of Information Technology, Maharaja Surajmal Institute of Technology, New Delhi, Email: muskanmhjn878@gmail.com, mayankg514@gmail.com, smriti.rout@gmail.com
Online published on 20 July, 2021.
Every field in this world is moving towards automation. Technology proves to be a tool that can create automated processes. Generative Adversarial Networks (GANs) are discovering structure in data which allows them to create realistic data. In this paper, we provide a comparative analysis of the two generative models to generate images which are tested on MNIST and Fashion MNIST datasets. Out of GAN and DCGAN, we determine the method which is more efficient with the minimum number of losses on the basis of different parameters.
Deep Learning, Generative Adversarial Networks, Deep Convolutional Generative Adversarial Networks
