Most network pruning methods rely on rule-of-thumb for human experts to prune the unimportant channels. This is time-consuming and can lead to suboptimal pruning. In this paper, we propose an effective SuperPruner algorithm, which aims to find optimal pruned structure instead of pruning unimportant channels. We first train a VerifyNet, a kind of super network, which is able to roughly evaluate the performance of any given network structure. The particle swarm optimization algorithm is then used to search for optimal network structure. Lastly, the weights in the VerifyNet are used as the initial weights of the optimal pruned structure to make fine-tuning. VerifyNet is a network performance evaluation; our algorithm can quickly prune the network under any hardware constraints. Our algorithm can be applied in multiple fields such as object recognition and semantic segmentation. Extensive experiment results demonstrate the effectiveness of SuperPruner. For example, on CIFAR-10, the pruned VGG16 achieves 93.18% Top-1 accuracy and reduces 74.19% of FLOPs and 89.25% of parameters. Compared with state-of-the-art methods, our algorithm can achieve higher pruned ratio with less accuracy cost.

中文翻译：

---

SuperPruner：通过超级网络自动修剪神经网络

大多数网络修剪方法依赖于人类专家的经验法则来修剪不重要的通道。这是耗时的，并且可能导致次优的修剪。在本文中，我们提出了一种有效的 SuperPruner 算法，旨在找到最佳的修剪结构而不是修剪不重要的通道。我们首先训练一个VerifyNet，一种超级网络，它能够粗略评估任何给定网络结构的性能。然后使用粒子群优化算法来搜索最佳网络结构。最后，VerifyNet 中的权重被用作最佳修剪结构的初始权重以进行微调。VerifyNet 是一个网络性能评估；我们的算法可以在任何硬件限制下快速修剪网络。我们的算法可以应用于多个领域，例如对象识别和语义分割。大量的实验结果证明了 SuperPruner 的有效性。例如，在 CIFAR-10 上，修剪后的 VGG16 实现了 93.18% 的 Top-1 准确率，并减少了 74.19% 的 FLOP 和 89.25% 的参数。与最先进的方法相比，我们的算法可以以更低的精度成本实现更高的修剪率。