Displaying 1 to 10 from 10 results

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

  •    Lua

This package includes CycleGAN, pix2pix, as well as other methods like BiGAN/ALI and Apple's paper S+U learning. The code was written by Jun-Yan Zhu and Taesung Park. Note: Please check out PyTorch implementation for CycleGAN and pix2pix. The PyTorch version is under active development and can produce results comparable or better than this Torch version.

pytorch-CycleGAN-and-pix2pix - Image-to-image translation in PyTorch (e

  •    Python

This is our PyTorch implementation for both unpaired and paired image-to-image translation. It is still under active development. The code was written by Jun-Yan Zhu and Taesung Park, and supported by Tongzhou Wang.




tensorflow-cyclegan - Lightweight CycleGAN tensorflow implementation 🦁 <-> 🐆

  •    Python

A lightweight CycleGAN tensorflow implementation. If you plan to use a CycleGAN model for real-world purposes, you should use the Torch CycleGAN implementation.

pytorch_cycle_gan - CycleGAN with Productive Generate APIs

  •    Python

this repo based on the original implementation of CycleGAN: https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix.git, in this version I reconstruct some code and made a generate API to simply generate image from your own single image and your trained model. I only trained about 50 epochs, but the result is fair enough for now. Laterly I will finish horse2zebra model, and update some more results.


CycleGAN-Tensorflow-PyTorch - CycleGAN Tensorflow PyTorch

  •    Python

2018.04.13: We modify the codes: use the newest tensorflow 1.7 API, and remove the redundancies. 2017.12.22: We add a simple PyTorch implementation, see the "pytorch" folder.

pixel-styler - Concise implementation of image-to-image translation.

  •    Python

This is a concise refactoring version of official PyTorch implementation for image-to-image translation. If you would like to apply a pre-trained model to a collection of input photos (without image pairs), please use --dataset_mode single and --model test options. Here's command to apply a model to Facade label maps (stored in the directory facades/testB).