Skip to content

Latest commit

 

History

History
63 lines (48 loc) · 2.19 KB

README.md

File metadata and controls

63 lines (48 loc) · 2.19 KB
Raw

MAGritte in PyTorch

Image manipulation detection and localization using Mixed Adversarial Generators. Code for the paper The Point Where Reality Meets Fantasy: Mixed Adversarial Generators for Image Splice Detection, NIPS 2019.

The code was written by Vladimir V. Kniaz and SolidHuman.

Note: The current software works well with PyTorch 1.2+ and Python 3.7+.

MAG: Project | Paper

Teaser

Prerequisites

  • Linux or macOS
  • Python 3
  • CPU or NVIDIA GPU + CUDA CuDNN

Getting Started

Installation

  • Clone this repo:
git clone https://github.com/vlkniaz/MAGritte
cd MAGritte
  • Install PyTorch 0.4+ and other dependencies (e.g., torchvision, visdom and dominate).
    • For pip users, please type the command pip install -r requirements.txt.
    • For Conda users, we provide a installation script ./scripts/conda_deps.sh. Alternatively, you can create a new Conda environment using conda env create -f environment.yml.

MAGritte train/test

  • Download a fantastic_reality dataset:
bash ./datasets/download_fantastic_reality_dataset.sh
  • Train a model:
bash ./scripts/train_magritte_edge.sh

  • To view training results and loss plots, run python -m visdom.server and click the URL http://localhost:8097. To see more intermediate results, check out ./checkpoints/magritte_magritte_edge/web/index.html.

  • Test the model:

bash ./scripts/test_magritte_edge.sh
  • The test results will be saved to a html file here: ./results/magritte_magritte_edge/test_latest/index.html.

Datasets

Download MAGritte dataset and create your own datasets.

Citation

If you use this code for your research, please cite our papers.

@inproceedings{MAG2019
...
}

Related Projects

ManTraNet | Fighting Fake News

Acknowledgments

Our code is based on pix2pix.