Projects sharing features with BigGAN PyTorch

simple generative adversarial network (GAN) using PyTorch

A pytorch implementation of Paper "Improved Training of Wasserstein GANs"

StyleGAN is a TensorFlow-based generative adversarial network framework designed for the synthesis of high-resolution synthetic imagery. It utilizes a style-based generator architecture to create realistic visual assets from latent vectors, focusing on the production of high-fidelity images. The system incorporates style mixing and stochastic noise injection to control visual attributes and fine-grained details. It uses adaptive instance normalization and progressive resolution upsampling to manage image quality and variety across different resolutions. The framework covers the full lifecycl

SPADE is a semantic image synthesis framework and generative adversarial network designed to transform semantic label maps into photorealistic images. It uses a spatially-adaptive normalization model to modulate activations based on semantic maps, ensuring that spatial layouts and details are preserved throughout the synthesis process. The project enables the generation of diverse image variations from a single semantic layout by integrating variational autoencoders and latent vector style control. These mechanisms allow for the adjustment of visual appearances and textures while keeping the

Collection of generative models in Pytorch version.

Code for the paper "Adversarial Generator-Encoder Networks"

Code for "On the Effects of Batch and Weight Normalization in Generative Adversarial Networks"

Tensorflow implementation for reproducing main results in the paper Self-Attention Generative Adversarial Networks by Han Zhang, Ian Goodfellow, Dimitris Metaxas, Augustus Odena.

A clean and readable Pytorch implementation of CycleGAN

pytorch implementation of fast-neural-style

Fast Neural Style for Image Style Transform by Pytorch

Pytorch-based tools for visualizing and understanding the neurons of a GAN. https://gandissect.csail.mit.edu/

A TensorFlow implementation of the Differentiable Neural Computer.

Convolutional neural network model for video classification trained on the Kinetics dataset.

Catalyst.GAN

This project is an unsupervised image restoration tool that uses a convolutional neural network as a structural prior to reconstruct images from noisy or incomplete data. It functions as a neural network image prior, utilizing the inherent biases of the network architecture to restore pixels without the need for a pre-trained dataset or external learning. The system performs zero-shot image restoration by treating the network architecture itself as a regularization term. It uses a randomly initialized encoder-decoder structure and iterative gradient descent to minimize pixel-wise loss, recove

Learning deep representations by mutual information estimation and maximization

PyTorch-GAN is a research-oriented framework providing a collection of modular implementations for generative adversarial network architectures. It serves as a toolkit for training and evaluating models that utilize adversarial minimax optimization to produce synthetic data, offering a structured environment for exploring complex generative tasks within the PyTorch ecosystem. The library distinguishes itself through a comprehensive suite of image synthesis and manipulation capabilities, including super-resolution, inpainting, and cross-domain style translation. It supports advanced training m

G-SchNet is a generative neural network that samples molecules by sequentially placing atoms in 3d space. It can be trained on data sets of 3d molecules with variable sizes and compositions. The conditional version, cG-SchNet, explicitly takes chemical and structural properties into account to…