williamSYSU / CatGAN

Codes for Category-aware Generative Adversarial Networks (AAAI 2020)

CatGAN: Category-aware Generative Adversarial Networks with Hierarchical Evolutionary Learning for Category Text Generation

The paper can be viewed here. Codes are available at TextGAN-PyTorch.

Requirements

• PyTorch >= 1.0.0
• Python 3.6
• Numpy 1.14.5
• CUDA 7.5+ (For GPU)
• nltk 3.4
• tqdm 4.32.1

To install, run pip install -r requirements.txt. In case of CUDA problems, consult the official PyTorch Get Started guide.

Environment

• OS: Linux
• GPU: NVIDIA TITAN Xp
• CUDA: 9.0
• cuDNN: v7

Datasets

Datasets can be downloaded here

Citation

If the code is used in your research, please star our repo and cite our paper as follows:

@inproceedings{liu2020catgan,
  title={CatGAN: Category-aware Generative Adversarial Networks with Hierarchical Evolutionary Learning for Category Text Generation},
  author={Liu, Zhiyue and Wang, Jiahai and Liang, Zhiwei},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  pages={},
  year={2020}
}