论文标题
模仿：迈向GAN研究的可重复性
Mimicry: Towards the Reproducibility of GAN Research
论文作者
论文摘要
推进生成对抗网络（GAN）研究的状态需要一个人与现有作品进行仔细，准确的比较。但是，当使用不同的框架以不同的方式实施模型时，这通常很难实现，即使使用相同的指标，也可以使用不同的程序进行评估。为了减轻这些问题，我们介绍了模仿，这是一个轻量级的Pytorch库，可提供流行的最先进的gans和评估指标的实现，以密切复制文献中报告的分数。我们通过在相同的条件下训练这些gans，在七个广泛使用的数据集中提供不同gan的全面基线性能，并使用相同的程序在三个流行的GAN指标上评估它们。可以在https://github.com/kwotsin/mimicry上找到该库。
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 evaluation metrics to closely reproduce reported scores in the literature. We provide comprehensive baseline performances of different GANs on seven widely-used datasets by training these GANs under the same conditions, and evaluating them across three popular GAN metrics using the same procedures. The library can be found at https://github.com/kwotsin/mimicry.
