573 Open source projects that are alternatives of or similar to Gan Compression

Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.

[NeurIPS 2018] Visual Object Networks: Image Generation with Disentangled 3D Representation.

Image-to-Image Translation in PyTorch

MATLAB implementations of Generative Adversarial Networks -- from GAN to Pixel2Pixel, CycleGAN

DEPRECATED: Depth Map Estimation from Monocular Images

PyTorch implementation of GANs (Generative Adversarial Networks). DCGAN, Pix2Pix, CycleGAN, SRGAN

Programming assignments and quizzes from all courses within the GANs specialization offered by deeplearning.ai

wgan, wgan2(improved, gp), infogan, and dcgan implementation in lasagne, keras, pytorch

Simple and extensible GAN image-to-image translation framework. Supports natural and medical images.

traiNNer: Deep learning framework for image and video super-resolution, restoration and image-to-image translation, for training and testing.

Generative Adversarial Networks implemented in PyTorch and Tensorflow

PyTorch (and PyTorch Lightning) implementation of Neural Style Transfer, Pix2Pix, CycleGAN, and Deep Dream!

Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV 2020, in PyTorch)

Implementation of the paper : "Toward Multimodal Image-to-Image Translation"

Voice Conversion by CycleGAN (语音克隆/语音转换): CycleGAN-VC2

PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, wav2lip, picture repair, image editing, photo2cartoon, image style transfer, and so on.

Toward Multimodal Image-to-Image Translation

Implementation of paper everybody dance now for Deep learning course project

AttentionGAN for Unpaired Image-to-Image Translation & Multi-Domain Image-to-Image Translation

StarNet

Master Deep Learning Algorithms with Extensive Math by Implementing them using TensorFlow

Generative Models Tutorial with Demo: Bayesian Classifier Sampling, Variational Auto Encoder (VAE), Generative Adversial Networks (GANs), Popular GANs Architectures, Auto-Regressive Models, Important Generative Model Papers, Courses, etc..

Data compression in TensorFlow

A portable, simple zip library written in C

AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.

A fast high compression read-only file system

[CVPR 2020 Workshop] A PyTorch GAN library that reproduces research results for popular GANs.

Caesium is a cross-platform image compression software aimed at helping photographers, bloggers, webmasters, businesses or casual users at storing, sending and sharing digital pictures. Based on libcaesium.

Rewriting a Deep Generative Model, ECCV 2020 (oral). Interactive tool to directly edit the rules of a GAN to synthesize scenes with objects added, removed, or altered. Change StyleGANv2 to make extravagant eyebrows, or horses wearing hats.

Extremely Fast Compression algorithm

Synthesizing and manipulating 2048x1024 images with conditional GANs

A simple integer compression library in Java

A user interface for Windows 10 filesystem compression

GAN-based Mel-Spectrogram Inversion Network for Text-to-Speech Synthesis

Generative Adversarial Transformers

Companion repository to GANs in Action: Deep learning with Generative Adversarial Networks

Draco is a library for compressing and decompressing 3D geometric meshes and point clouds. It is intended to improve the storage and transmission of 3D graphics.

A clean and readable Pytorch implementation of CycleGAN

JNI binding for Zstd

Transfer 10Gbps http traffic over 1Gbps networks :)

秒级! 三行代码实现iOS视频压缩、变速、混音、合并、GIF水印、旋转、换音、裁剪 ! 支持不同分辩率，支持你能想到的各种混合操作! 扩展性强...更多功能不断增加中... iOS 8.0 + 有需要的功能或错误欢迎issue，笔者会及时更新

High performance (de)compression in an 8kB package

A Fast Deep Learning Model to Upsample Low Resolution Videos to High Resolution at 30fps

Lizard (formerly LZ5) is an efficient compressor with very fast decompression. It achieves compression ratio that is comparable to zip/zlib and zstd/brotli (at low and medium compression levels) at decompression speed of 1000 MB/s and faster.

Lepton is a tool and file format for losslessly compressing JPEGs by an average of 22%.

DeepNude's algorithm and general image generation theory and practice research, including pix2pix, CycleGAN, UGATIT, DCGAN, SinGAN, ALAE, mGANprior, StarGAN-v2 and VAE models (TensorFlow2 implementation). DeepNude的算法以及通用生成对抗网络（GAN,Generative Adversarial Network）图像生成的理论与实践研究。

Interactive Image Generation via Generative Adversarial Networks

Dockerized PHP7 application runs as a Microservice to resize and crop images on the fly. Get optimised images with MozJPEG, WebP or PNG using ImageMagick. Includes face detection, cropping, face blurring, image rotation and many other options. Abstract storage based on FlySystem in order to store images on any provider (local, AWS S3...).

A blocking, shuffling and loss-less compression library that can be faster than `memcpy()`.

Pytorch implementation of MixNMatch

Fastest Integer Compression

Compressed numerical arrays that support high-speed random access

ZSON is a PostgreSQL extension for transparent JSONB compression

Lightning Fast Serialization of Data Frames for R

Voice Converter Using CycleGAN and Non-Parallel Data

A compressed bitmap class in C++.

lightweight lossless file minifier/optimizer

a high performance, general purpose data compressor written in rust

A C library for reading, creating, and modifying zip archives.

[CVPR 2021] Anycost GANs for Interactive Image Synthesis and Editing