Image-to-Image Translation in PyTorch

Bringing Old Photo Back to Life (CVPR 2020 oral)

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

🧠💬 Articles I wrote about machine learning, archived from MachineCurve.com.

Synthetic data generation for tabular data

A denoising autoencoder + adversarial losses and attention mechanisms for face swapping.

The author's officially unofficial PyTorch BigGAN implementation.

Implementation of papers in 100 lines of code.

EdgeConnect: Structure Guided Image Inpainting using Edge Prediction, ICCV 2019 https://arxiv.org/abs/1901.00212

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

A sketch extractor for anime/illustration.

A simple interface for editing natural photos with generative neural networks.

State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.

Synthetic data generators for tabular and time-series data

A very simple generative adversarial network (GAN) in PyTorch

Toward Multimodal Image-to-Image Translation

Official PyTorch repo for JoJoGAN: One Shot Face Stylization

Research Framework for easy and efficient training of GANs based on Pytorch

Generative Adversarial Transformers

[NeurIPS 2020] Differentiable Augmentation for Data-Efficient GAN Training