GANs CelebA

I built a GAN that can generate realistic images of fake people.

Generative Adversarial Networks (GAN) using Keras.

GAN and WGAN experiments on MNIST and CelebA (Written for ECE6254 Final Project)

GANs 101 and its Applications: An exploration of DCGAN, WGAN, LSGAN and GAN transfer learning on the CelebA dataset

Progressive GAN on celebrity faces

A study on the interpretability of the concepts learned by Prototypical Part Networks (ProtoPNets) on the CUB200-2011 and CelebAMask datasets.

Python-based software for potential assailants composite sketches generation with AI

Project in Advanced Computer Vision course in NTU

A GAN that sythesizes new faces alike faces from celebA dataset

Workshop material for the Bias+Images Festival, California, 2021

Using Deep Convolutional GAN (generative adversarial network) to generate realistic faces, trained using the celebA dataset, implemented using pytorch c++ frontend.

Face generation using generative adversarial networks to generate new images

Use GANs with normalization techniques like dropouts, batch normalization along with having a low variance in kernel weight initialization, achieve realistic images of faces trained on the CelebA dataset. Images also have been generated of hand written digits after being trained on the MNIST dataset. This would be useful for generating training …

Dynamic Schedule Task on VGG16 using pytorch

Generative Adversarial Network that creates images of handwritten numeral digits or faces

Experiments that accompany a paper in which Transfer-Learning applied to GAN is examined