论文标题
FusedProp：进行有效培训生成的对抗网络
FusedProp: Towards Efficient Training of Generative Adversarial Networks
论文作者
论文摘要
生成的对抗网络（GAN）能够生成惊人的现实样本，但是最先进的甘罐在训练上可能非常昂贵。在本文中，我们提出了融合的繁殖（FusedProp）算法，该算法可用于有效地训练鉴别器和共同gan的发电机，并仅使用一个前进和一个向后传播。我们表明，与常规的甘斯训练相比，FusedProp的训练速度达到了1.49倍，尽管需要进一步的研究以提高其稳定性。通过报告我们的初步结果和开放式实施，我们希望加快对甘纳斯培训的未来研究。
Generative adversarial networks (GANs) are capable of generating strikingly realistic samples but state-of-the-art GANs can be extremely computationally expensive to train. In this paper, we propose the fused propagation (FusedProp) algorithm which can be used to efficiently train the discriminator and the generator of common GANs simultaneously using only one forward and one backward propagation. We show that FusedProp achieves 1.49 times the training speed compared to the conventional training of GANs, although further studies are required to improve its stability. By reporting our preliminary results and open-sourcing our implementation, we hope to accelerate future research on the training of GANs.
