[//]: # (Must have only one H1 heading)
# pix2pixHD

[//]: # (Must have H2 heading for overview or introduction - displayed as tab)
## Overview
[Project](https://tcwang0509.github.io/pix2pixHD/) | [YouTube](https://youtu.be/3AIpPlzM_qs) | [Paper](https://arxiv.org/pdf/1711.11585.pdf)

Pix2PixHD is a Pytorch implementation of a deep learning-based method for high-resolution (e.g. 2048x1024) photorealistic image-to-image translation. It can be used for turning semantic label maps into photo-realistic images or synthesizing portraits from face label maps. 


[High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://tcwang0509.github.io/pix2pixHD/) in CVPR 2018.

The pix2pixHD model is available for commercial use via a [Berkeley Software Distribution (BSD)](https://opensource.org/licenses/BSD-3-Clause) License. 

[//]: # (Must have H2 heading for overview or introduction - displayed as tab)
## Datasets
- We use the Cityscapes dataset. To train a model on the full dataset, please download it from the [official website](https://www.cityscapes-dataset.com/) (registration required).
After downloading, please put it under the `datasets` folder in the same way the example images are provided.

[//]: # (Must have H2 heading for metadata - used for card attributes)
## Metadata
[//]: # (Required attributes for in this section)
- Linux or macOS
- Python 2 or 3
- NVIDIA GPU (11G memory or larger) + CUDA cuDNN
- Install PyTorch and dependencies from the [NGC Container Registry](https://ngc.nvidia.com/catalog/containers/nvidia:pytorch)
- Install python libraries [dominate](https://github.com/Knio/dominate)

pix2pixhd

Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic image-to-image translation.