eduzhai > Applied Sciences > Engineering >

Measuring Performance of Generative Adversarial Networks on Devanagari Script

  • king
  • (0) Download
  • 20210506
  • Save

... pages left unread,continue reading

Document pages: 5 pages

Abstract: The working of neural networks following the adversarial philosophy to createa generative model is a fascinating field. Multiple papers have alreadyexplored the architectural aspect and proposed systems with potentially goodresults however, very few papers are available which implement it on areal-world example. Traditionally, people use the famous MNIST dataset as aHello, World! example for implementing Generative Adversarial Networks (GAN).Instead of going the standard route of using handwritten digits, this paperuses the Devanagari script which has a more complex structure. As there is noconventional way of judging how well the generative models perform, threeadditional classifiers were built to judge the output of the GAN model. Thefollowing paper is an explanation of what this implementation has achieved.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×