Face generation project for the DLND, Project 5
-
Updated
Dec 2, 2017 - 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.
Face generation project for the DLND, Project 5
Udacity DLND final project . Use GAN generate face
Projects for Udacity Deep Learning Nanodegree Program: CNN, RNN, GANs
💤🖌️ AI making tiny Bitsy video games. Features an experimental generative structure inspired by GANs and Genetic Algorithms
Utility files for Granular challenge.
Define and Train DCGAN generator network to generate new images of faces that look as realistic as possible.
In this project, I’ve used Generative Adversarial Networks (GANs) to generate new images of human faces from scratch, based on the neural networks being trained on real human faces. I used the MNIST dataset and CelebFaces Attributes (CelebA) dataset in this project.
Its a image generation library which learns to generate patterns based on training data
Cardiac Fats Segmentation Using a Conditional Generative Adversarial Network
A framework to synthsize Brain data using AI models
Generate images to handle imbalanced datasets using DCGAN
Experiments with Baudelaire and a text-to-image GAN.
Defined and trained a DCGAN on a dataset of faces. The Goal of this project is to generate new images of faces that look as realistic as possible.
Implementation of Conditional Deep Convolutional GANs in low-level APIs
Built a real-time website for image generation using gan-cls algorithm. The algorithm is trained on CUBS 200 birds dataset.
A deep neural network for kernel-blind image deblurring
Released June 10, 2014