Corpus ID: 218516651

Mimicry: Towards the Reproducibility of GAN Research

@article{Lee2020MimicryTT,
  title={Mimicry: Towards the Reproducibility of GAN Research},
  author={Kwot Sin Lee and Christopher Town},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.02494}
}
  • Kwot Sin Lee, Christopher Town
  • Published 2020
  • Computer Science
  • ArXiv
  • Advancing the state of Generative Adversarial Networks (GANs) research requires one to make careful and accurate comparisons with existing works. Yet, this is often difficult to achieve in practice when models are often implemented differently using varying frameworks, and evaluated using different procedures even when the same metric is used. To mitigate these issues, we introduce Mimicry, a lightweight PyTorch library that provides implementations of popular state-of-the-art GANs and… CONTINUE READING

    Tables and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 45 REFERENCES
    The fate of petroleum in soil ecosystems
    400
    A PGC-1α Isoform Induced by Resistance Training Regulates Skeletal Muscle Hypertrophy
    392
    GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
    1602
    Infomax-gan: Mutual information maximization for improved adversarial image generation
    • 2019