Synthesizing Informative Training Samples with GAN [PDF]

The experiment data have been released in Google Drive. The released data include: [1] pretrained BigGAN Generators; [2] GAN Inversion learned latent vectors (z); [3] IT-GAN learned latent vectors (z).

We also provide some raw training codes which have been neither re-organized nor validated. Just for reference. The raw training code is here. Replace md_utils.py with utils.py, md_networks.py with networks.py if applicable.

Citation

@article{zhao2022synthesizing,
  title={Synthesizing Informative Training Samples with GAN},
  author={Zhao, Bo and Bilen, Hakan},
  journal={NeurIPS 2022 Workshop on Synthetic Data for Empowering ML Research},
  year={2022}
}