Utility files for Granular challenge.
-
Updated
Apr 14, 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.
Utility files for Granular challenge.
Generating balanced multiplayer game levels with GANs and RL.
Deep Convolutional Generative Adversarial Network using Keras
PyTorch Generative adversarial networks
The experimental codes using Keras from the paper that was accepted to GECCO 2019.
A delira-compatible cycle-GAN skeleton.
Using GAN to create points of a certain function
Various generative models to generate new images based on various datasets
Applying PBT optimization technique to different domains
Reproducing results of HVAE paper, by implementing vanilla VAE, HVAE (with VampPrior), GAN, and DCGAN.
JPEG圧縮過程を利用したDCGANです。PyTorchへ移行しました。https://github.com/kthksgy/jpeg-dcgan-pytorch
Generative Adversarial Networks (GANs) to recover features in astronomy images🪐💫⭐️
Artificial Intelligence able to generate fake images, such as faces or landscapes, which appear real from a human point of view.
Using Convolution neural network to regenerate 0-9 digits at high quality.
Computer Vision Algorithm receiving a Street-Level Picture and Predicting the City it has been shot in. Jump to the README, have a look at the code, and then try it yourself.
Keras implementation of AnoGAN model.
Released June 10, 2014