AttGAN-Cartoon
_{TIP Nov. 2019, arXiv Nov. 2017}

Example of using repo. AttGAN-Tensorflow on a cartoon dataset. We make modifications to the files below to adapt the repo. AttGAN-Tensorflow to the cartoon dataset. Please use a diff tool to show the differences of these files from the original ones in AttGAN-Tensorflow, then you can find out what modifications we should make to AttGAN-Tensorflow for a custom dataset.

• data.py
• train.py
• test.py, test_multi.py, test_slide.py

Usage

• Environment

  • Python 3.6

  • TensorFlow 1.15

  • OpenCV, scikit-image, tqdm, oyaml

  • we recommend Anaconda or Miniconda, then you can create the AttGAN environment with commands below

    conda create -n AttGAN python=3.6
    
    source activate AttGAN
    
    conda install opencv scikit-image tqdm tensorflow-gpu=1.15
    
    conda install -c conda-forge oyaml
    

  • NOTICE: if you create a new conda environment, remember to activate it before any other command

    source activate AttGAN
    

• Data Preparation

  • Cartoon Set

    • download cartoonset10k.tgz (move to ./data/cartoonset10k.tgz)

    • unzip and process the data

      cd ./data
      
      tar zxvf cartoonset10k.tgz
      
      python prepare_dataset.py
      

• Run AttGAN

  • training

    CUDA_VISIBLE_DEVICES=0 \
    python train.py \
    --load_size 143 \
    --crop_size 128 \
    --model model_128 \
    --experiment_name AttGAN_128
    

  • testing

    • single attribute editing (inversion)

      CUDA_VISIBLE_DEVICES=0 \
      python test.py \
      --experiment_name AttGAN_128
      

    • multiple attribute editing (inversion) example

      CUDA_VISIBLE_DEVICES=0 \
      python test_multi.py \
      --test_att_names face_color_0 hair_color_0 \
      --experiment_name AttGAN_128
      

    • attribute sliding example

      CUDA_VISIBLE_DEVICES=0 \
      python test_slide.py \
      --test_att_name face_color_0 \
      --test_int_min -2 \
      --test_int_max 2 \
      --test_int_step 0.5 \
      --experiment_name AttGAN_128
      

  • loss visualization

    CUDA_VISIBLE_DEVICES='' \
    tensorboard \
    --logdir ./output/AttGAN_128/summaries \
    --port 6006
    

  • convert trained model to .pb file

    python to_pb.py --experiment_name AttGAN_128
    

Citation

If you find AttGAN useful in your research work, please consider citing:

@ARTICLE{8718508,
author={Z. {He} and W. {Zuo} and M. {Kan} and S. {Shan} and X. {Chen}},
journal={IEEE Transactions on Image Processing},
title={AttGAN: Facial Attribute Editing by Only Changing What You Want},
year={2019},
volume={28},
number={11},
pages={5464-5478},
keywords={Face;Facial features;Task analysis;Decoding;Image reconstruction;Hair;Gallium nitride;Facial attribute editing;attribute style manipulation;adversarial learning},
doi={10.1109/TIP.2019.2916751},
ISSN={1057-7149},
month={Nov},}