Project for Deep Learning Nanodegree, unit 5 (Generative Adversarial Networks).
-
Updated
Mar 20, 2022 - HTML
Generative adversarial networks (GAN) are a class of generative machine learning frameworks. A GAN consists of two competing neural networks, often termed the Discriminator network and the Generator network. GANs have been shown to be powerful generative models and are able to successfully generate new data given a large enough training dataset.
Project for Deep Learning Nanodegree, unit 5 (Generative Adversarial Networks).
In this project, I have used generative adversarial networks to generate new images of faces, over CelebA dataset.
Udacity Deep Learning Nanodegree Face Generation PyTorch Project using DCGAN
In this project, you'll use generative adversarial networks to generate new images of faces.
My work from the Deep Learning Nanodegree Program
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 …
This repo contains basic GAN network to generate faces.
A deep convolutional generative adversarial network (DCGAN) for generating faces.
A generative adversarial network (GAN) that generates images of faces.
This project aims to fuse 2 tracks of music together, using two methods. A Variational Auto Encoder and a Generative Adversarial Network.
Udacity - Deep Learning - Project 5 (GAN TensorFlow) - Face Generation - Submit Files Only - Passed Wed 20 Sep 2017
Use of Generative Adversarial Networks (GAN's) to generate new images of faces.
This is Udacity - Deep Learning Project 4 - Generate Faces
A project that deals with GANs and image generation using deep learning and adversarial methods in order to generate faces. This Project is mandatory in the Udacity Nanodegree Program that i am pursuing. I will be commenting on the key learning from this project here.
Demo Page for "Generative Models for Improved Naturalness, Intelligibility, and Voicing of Whispered Speech" (SLT22)
Used generative adversarial networks to generate new images of faces.
A generative adversarial network that trains on photos celebrities faces to produce new realistic face images
A generative adversarial networks model fast style transfer application.
This project uses generative adversarial networks (GAN) to generate new images of faces.
Released June 10, 2014