Hand-digit generation using basicGAN on MNIST dataset
![Board](https://github.com/images/1.png)
Results on DCGAN on MNIST and CelebA dataset
![Board](https://github.com/images/2.png)
Result of cGAN on MNIST, FMNIST and CIFAR
![Board](https://github.com/images/3.png)
Result of infoGAN on MNIST, FMNIST and CIFAR
![Board](https://github.com/images/4.png)
Result of infoGAN on MNIST, FMNIST and CIFAR
![Board](https://github.com/images/5.png)
![Board](https://github.com/images/6.png)
![Board](https://github.com/images/7.png)
![Board](https://github.com/images/8.png)
Left to Right: (1) Low resolution image (LR) which is also the inputs to our model (2)
High Resolution image (HR) which is ground truth image for evaluating image [4x
resolution of LR] (3) Super resolution image (SR) which is the generated image from the
![Board](https://github.com/images/9.png)
Self Attention module and other stabilizing method applied on DCGAN as proposed in
the paper SAGAN. Above results suggest that our model has overcome the problem of
long range dependencies which can clearly be seen in initial epoch’s result.
![Board](https://github.com/images/10.png)