Generate faces using General Adversarial networks
-
Updated
Sep 26, 2017 - Jupyter Notebook
Generate faces using General Adversarial networks
Pytorch implementation of Generative Adversarial Networks (GAN) for MNIST and EMNIST datasets
A blog which talks about machine learning, deep learning algorithms and the Math. and Machine learning algorithms written from scratch.
Generative Adversarial Networks for CIFAR-10 dataset written as part of my MSc in Data Science degree.
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.
Attempt to build a GAN based data repeater to enable our team to generate more data with "statistically adequate" fake data.
Generating fake images using Deep Convolutional GANs (DCGAN)
A GAN that sythesizes new faces alike faces from celebA dataset
Generating audio using a Generative Adversarial Network
Chess game including state-of-the-art GUI, lichess.org game selection interface and review mechanic and a simple computer opponent to play against.
DCGAN implementation in keras on CIFAR10 dataset
Notebooks completed to learn various Deep Learning topics during Inspirit AI's Deep Dives: Designing Deep Learning Systems program(500+ lines)
Contains implementation of a GAN to generate human faces.
Generation and Prediction of Images Using KERAS
Automatic Tiger Surveillance using YOLOv8 and EnlightenGAN aimed for Tiger Conservation
Presentation material for my talk at Pycon DE 2023: Intro on synthetic tabular data including synthetic data generation, evaluation metrics and common problems of synthetic data generation projects.
Add a description, image, and links to the general-adversarial-network topic page so that developers can more easily learn about it.
To associate your repository with the general-adversarial-network topic, visit your repo's landing page and select "manage topics."