Skip to content
master
Switch branches/tags
Go to file
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

README.md

Exemplar Guided Unsupervised Image-to-Image Translation with Semantic Consistency

Tensorflow implementation of ICLR 2019 paper Exemplar Guided Unsupervised Image-to-Image Translation with Semantic Consistency

alt text

Network architecture

alt text

Information flow diagrams

alt text

Dependencies

  • python 3.6.9
  • tensorflow-gpu (1.14.0)
  • numpy (1.14.0)
  • Pillow (5.0.0)
  • scikit-image (0.13.0)
  • scipy (1.0.1)
  • matplotlib (2.0.0)

Resources

  • Pretrained models: MNIST, MNIST_multi, GTA<->BDD, CelebA, VGG19
  • Training & Testing data in tf-record format: MNIST, MNIST_multi. GTA<->BDD, CelebA. Note: For the GTA<->BDD experiment, the data are prepared with RGB images of 512x1024 resolution, and segmentation labels of 8 categories. They are provided used for further research. In our paper, we use RGB images of 256x512 resolution without and segmentation labels.
  • Segmentation model Refer to DeepLab-ResNet-TensorFlow

TF-record data preparation steps (Optional)

You can skip this data preparation procedure if directly using the tf-record data files.

  1. cd datasets
  2. ./run_convert_mnist.sh to download and convert mnist and mnist_multi to tf-record format.
  3. ./run_convert_gta_bdd.sh to convert the images and segmentation to tf-record format. You need to download data from GTA5 website and BDD website. Note: this script will reuse gta data downloaded and processed in ./run_convert_gta_bdd.sh
  4. ./run_convert_celeba.sh to convert the images to tf-record format. You can directly download the prepared data or download and process data from CelebA website .

Training steps

  1. Replace the links data, logs, weights with your own directories or links.
  2. Download VGG19 into 'weights' directory.
  3. Download the tf-record training data to the data_parent_dir (default ./data).
  4. Modify the data_parent_dir, checkpoint_dir and comment/uncomment the target experiment in the run_train_feaMask.sh and run_train_EGSCIT.sh scripts.
  5. Run run_train_feaMask.sh to pretrain the feature mask network. Then run run_train_EGSCIT.sh.

Testing steps

  1. Replace the links data, logs, weights with your own directories or links.
  2. (Optional) Download the pretrained models to the checkpoint_dir (default ./logs).
  3. Download the tf-record testing data to the data_parent_dir (default ./data).
  4. Modify the data_parent_dir, checkpoint_dir and comment/uncomment the target experiment in the run_test_EGSCIT.sh script.
  5. run run_test_EGSCIT.sh.

Citation

@article{ma2018exemplar,
  title={Exemplar Guided Unsupervised Image-to-Image Translation with Semantic Consistency},
  author={Ma, Liqian and Jia, Xu and Georgoulis, Stamatios and Tuytelaars, Tinne and Van Gool, Luc},
  journal={ICLR},
  year={2019}
}

Related projects

About

Tensorflow implementation of ICLR2019 paper "Exemplar Guided Unsupervised Image-to-Image Translation with Semantic Consistency"

Topics

Resources

Releases

No releases published

Packages

No packages published