Pruning is an effective technique for convolutional neural networks (CNNs) model compression, but it is difficult to find the optimal pruning policy due to the large design space. To improve the usability of pruning, many auto pruning methods have been developed. Recently, Bayesian optimization (BO) has been considered to be a competitive algorithm for auto pruning due to its solid theoretical foundation and high sampling efficiency. However, BO suffers from the curse of dimensionality. The performance of BO deteriorates when pruning deep CNNs, since the dimension of the design spaces increase. We propose a novel clustering algorithm that reduces the dimension of the design space to speed up the searching process. Subsequently, a rollback algorithm is proposed to recover the high-dimensional design space so that higher pruning accuracy can be obtained. We validate our proposed method on ResNet, MobileNetV1, and MobileNetV2 models. Experiments show that the proposed method significantly improves the convergence rate of BO when pruning deep CNNs with no increase in running time. The source code is available at https://github.com/fanhanwei/BOCR.
翻译:Pruning是进化神经网络模型压缩的一种有效技术,但由于设计空间大,很难找到最佳的修剪政策。为了提高修剪的可用性,已经开发了许多自动修剪方法。最近,Bayesian优化(BO)因其坚实的理论基础和高采样效率而被认为是自动修剪的一种竞争性算法。然而,BO受到维度的诅咒。BO的性能由于设计空间的维度增大而恶化。我们建议采用新的组合算法,减少设计空间的维度,以加快搜索进程。随后,建议采用滚动算法,以恢复高维设计空间,从而获得更高的修剪剪精度。我们验证了ResNet、MmobleNetV1和MobleNetV2模型上的拟议方法。实验显示,拟议的方法在钻练深度CNN时,在不增加运行时间的情况下,会大大改善BO的趋同率。源代码可在 https://github.com/fanhanwe/BOCR。