Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/nvidia/pix2pixhd
Synthesizing and manipulating 2048x1024 images with conditional GANs
https://github.com/nvidia/pix2pixhd
computer-graphics computer-vision deep-learning deep-neural-networks gan generative-adversarial-network image-to-image-translation pix2pix pytorch
Last synced: 7 days ago
JSON representation
Synthesizing and manipulating 2048x1024 images with conditional GANs
- Host: GitHub
- URL: https://github.com/nvidia/pix2pixhd
- Owner: NVIDIA
- License: other
- Created: 2017-12-01T19:19:14.000Z (about 7 years ago)
- Default Branch: master
- Last Pushed: 2024-11-04T18:13:20.000Z (3 months ago)
- Last Synced: 2025-01-06T23:13:46.762Z (14 days ago)
- Topics: computer-graphics, computer-vision, deep-learning, deep-neural-networks, gan, generative-adversarial-network, image-to-image-translation, pix2pix, pytorch
- Language: Python
- Homepage: https://tcwang0509.github.io/pix2pixHD/
- Size: 54.4 MB
- Stars: 6,696
- Watchers: 169
- Forks: 1,402
- Open Issues: 247
-
Metadata Files:
- Readme: README.md
- License: LICENSE.txt
Awesome Lists containing this project
README
# pix2pixHD
### [Project](https://tcwang0509.github.io/pix2pixHD/) | [Youtube](https://youtu.be/3AIpPlzM_qs) | [Paper](https://arxiv.org/pdf/1711.11585.pdf)
Pytorch implementation of our 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/)
[Ting-Chun Wang](https://tcwang0509.github.io/)1, [Ming-Yu Liu](http://mingyuliu.net/)1, [Jun-Yan Zhu](http://people.eecs.berkeley.edu/~junyanz/)2, Andrew Tao1, [Jan Kautz](http://jankautz.com/)1, [Bryan Catanzaro](http://catanzaro.name/)1
1NVIDIA Corporation, 2UC Berkeley
In CVPR 2018.
## Image-to-image translation at 2k/1k resolution
- Our label-to-streetview results
- Interactive editing results
- Additional streetview results
- Label-to-face and interactive editing results
- Our editing interface
## Prerequisites
- Linux or macOS
- Python 2 or 3
- NVIDIA GPU (11G memory or larger) + CUDA cuDNN
## Getting Started
### Installation
- Install PyTorch and dependencies from http://pytorch.org
- Install python libraries [dominate](https://github.com/Knio/dominate).
```bash
pip install dominate
```
- Clone this repo:
```bash
git clone https://github.com/NVIDIA/pix2pixHD
cd pix2pixHD
```
### Testing
- A few example Cityscapes test images are included in the `datasets` folder.
- Please download the pre-trained Cityscapes model from [here](https://drive.google.com/file/d/1OR-2aEPHOxZKuoOV34DvQxreqGCSLcW9/view?usp=drive_link) (google drive link), and put it under `./checkpoints/label2city_1024p/`
- Test the model (`bash ./scripts/test_1024p.sh`):
```bash
#!./scripts/test_1024p.sh
python test.py --name label2city_1024p --netG local --ngf 32 --resize_or_crop none
```
The test results will be saved to a html file here: `./results/label2city_1024p/test_latest/index.html`.
More example scripts can be found in the `scripts` directory.
### Dataset
- 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.
### Training
- Train a model at 1024 x 512 resolution (`bash ./scripts/train_512p.sh`):
```bash
#!./scripts/train_512p.sh
python train.py --name label2city_512p
```
- To view training results, please checkout intermediate results in `./checkpoints/label2city_512p/web/index.html`.
If you have tensorflow installed, you can see tensorboard logs in `./checkpoints/label2city_512p/logs` by adding `--tf_log` to the training scripts.
### Multi-GPU training
- Train a model using multiple GPUs (`bash ./scripts/train_512p_multigpu.sh`):
```bash
#!./scripts/train_512p_multigpu.sh
python train.py --name label2city_512p --batchSize 8 --gpu_ids 0,1,2,3,4,5,6,7
```
Note: this is not tested and we trained our model using single GPU only. Please use at your own discretion.
### Training with Automatic Mixed Precision (AMP) for faster speed
- To train with mixed precision support, please first install apex from: https://github.com/NVIDIA/apex
- You can then train the model by adding `--fp16`. For example,
```bash
#!./scripts/train_512p_fp16.sh
python -m torch.distributed.launch train.py --name label2city_512p --fp16
```
In our test case, it trains about 80% faster with AMP on a Volta machine.
### Training at full resolution
- To train the images at full resolution (2048 x 1024) requires a GPU with 24G memory (`bash ./scripts/train_1024p_24G.sh`), or 16G memory if using mixed precision (AMP).
- If only GPUs with 12G memory are available, please use the 12G script (`bash ./scripts/train_1024p_12G.sh`), which will crop the images during training. Performance is not guaranteed using this script.
### Training with your own dataset
- If you want to train with your own dataset, please generate label maps which are one-channel whose pixel values correspond to the object labels (i.e. 0,1,...,N-1, where N is the number of labels). This is because we need to generate one-hot vectors from the label maps. Please also specity `--label_nc N` during both training and testing.
- If your input is not a label map, please just specify `--label_nc 0` which will directly use the RGB colors as input. The folders should then be named `train_A`, `train_B` instead of `train_label`, `train_img`, where the goal is to translate images from A to B.
- If you don't have instance maps or don't want to use them, please specify `--no_instance`.
- The default setting for preprocessing is `scale_width`, which will scale the width of all training images to `opt.loadSize` (1024) while keeping the aspect ratio. If you want a different setting, please change it by using the `--resize_or_crop` option. For example, `scale_width_and_crop` first resizes the image to have width `opt.loadSize` and then does random cropping of size `(opt.fineSize, opt.fineSize)`. `crop` skips the resizing step and only performs random cropping. If you don't want any preprocessing, please specify `none`, which will do nothing other than making sure the image is divisible by 32.
## More Training/Test Details
- Flags: see `options/train_options.py` and `options/base_options.py` for all the training flags; see `options/test_options.py` and `options/base_options.py` for all the test flags.
- Instance map: we take in both label maps and instance maps as input. If you don't want to use instance maps, please specify the flag `--no_instance`.
## Citation
If you find this useful for your research, please use the following.
```
@inproceedings{wang2018pix2pixHD,
title={High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs},
author={Ting-Chun Wang and Ming-Yu Liu and Jun-Yan Zhu and Andrew Tao and Jan Kautz and Bryan Catanzaro},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
year={2018}
}
```
## Acknowledgments
This code borrows heavily from [pytorch-CycleGAN-and-pix2pix](https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix).