/Generate-Faces-Using-GAN

Primary LanguageJupyter NotebookMIT LicenseMIT

Deep Learning

Generate-Faces-Using-GAN

Overview

Training a Deep Convolutional Generative Adversarial Network (DCGAN) on a dataset of faces to train it to generate new images of faces that look as realistic as possible

Defining the Model

A GAN is comprised of two adversarial networks, a discriminator and a generator.

Note

Run only if GPU is Avaiable. Warning : Don't Run on CPU

GAN

GANs are generative models: they create new data instances that resemble your training data. For example, GANs can create images that look like photographs of human faces, even though the faces don't belong to any real person.