A Generative Adversarial Network (GAN) project designed to generate realistic fake handwritten digits, trained on the MNIST dataset.
-
Updated
May 31, 2024 - Jupyter Notebook
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.
A Generative Adversarial Network (GAN) project designed to generate realistic fake handwritten digits, trained on the MNIST dataset.
Extreme value theory and GANs to generate compound coastal hazards (wind speed + sea level pressure) from ERA5 reanalysis data over the Bay of Bengal.
FaultGuard: A Generative Approach to Resilient Fault Prediction in Smart Electrical Grids
Official implementation of DrugGEN
HyMPS will be a platform-indipendent software suite for advanced audio/video contents production.
Implementation of the Style GAN Architecture in PyTorch
Benchmarking synthetic data generation methods.
PyTorch implementation (with up-to-date tooling) of the SAM / DAC algorithm
A machine learning library for detecting anomalies in signals.
Image Domain Transfer with CycleGAN
Just some notebooks I wrote to research some fun stuff in hobby time
This repository contains an implementation of a Deep Convolutional Generative Adversarial Network (DCGAN) trained on the FashionMNIST dataset. The project aims to generate realistic images of clothing items using a GAN architecture. It includes model definitions, training scripts, and visualizations of generated images at various training stages.
Synthetic data generation for tabular data
State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.
MONAI Generative Models makes it easy to train, evaluate, and deploy generative models and related applications
This is part of my dissertation thesis. I'm trying to denoise historical hungarian folk-musical recordings based on Google's article: https://arxiv.org/pdf/2008.02027
[CVPR 2023, top-10%] Authors official PyTorch implementation of the "Attribute-preserving Face Dataset Anonymization via Latent Code Optimization".
Using WGAN-gp and creating art portraits.
Repo for all the SRIP 2024 work at CVIG Lab IITGN under Prof. Shanmuganathan Raman
Synthetic data generators for tabular and time-series data
Released June 10, 2014