The intensive computation and memory requirements of generative adversarial
neural networks (GANs) hinder its real-world deployment on edge devices such as
smartphones. Despite the success in model reduction of CNNs, neural network
quantization methods have not yet been studied on GANs, which are mainly faced
with the issues of both the effectiveness of quantization algorithms and the
instability of training GAN models. In this paper, we start with an extensive
study on applying existing successful methods to quantize GANs. Our observation
reveals that none of them generates samples with reasonable quality because of
the underrepresentation of quantized values in model weights, and the generator
and discriminator networks show different sensitivities upon quantization
methods. Motivated by these observations, we develop a novel quantization
method for GANs based on EM algorithms, named as QGAN. We also propose a
multi-precision algorithm to help find the optimal number of bits of quantized
GAN models in conjunction with corresponding result qualities. Experiments on
CIFAR-10 and CelebA show that QGAN can quantize GANs to even 1-bit or 2-bit
representations with results of quality comparable to original models.

本文研究了如何在仿射神经网络中量化生成对抗神经网络并提出了一种基于 EM 算法的 QGAN 方法方法，同时还提出了一种多精度算法，可帮助找到量化 GAN 模型的最佳位数以及相应的结果质量。实验结果表明，QGAN 可将 GAN 量化为 1/2 比特表示，结果质量与原始模型相当。