Filter pruning of convolutional neural networks (CNNs) is a common technique to effectively reduce the memory footprint, the number of arithmetic operations, and, consequently, inference time. Recent pruning approaches also consider the targeted device (i.e., graphics processing units) for CNN deployment to reduce the actual inference time. However, simple metrics, such as the \(\ell ^1\)-norm, are used for deciding which filters to prune. In this work, we propose a hardware-aware technique to explore the vast multi-objective design space of possible filter pruning configurations. Our approach incorporates not only the targeted device but also techniques from explainable artificial intelligence for ranking and deciding which filters to prune. For each layer, the number of filters to be pruned is optimized with the objective of minimizing the inference time and the error rate of the CNN. Experimental results show that our approach can speed up inference time by 1.40× and 1.30× for VGG-16 on the CIFAR-10 dataset and ResNet-18 on the ILSVRC-2012 dataset, respectively, compared to the state-of-the-art ABCPruner.

卷积神经网络 (CNN) 的滤波器剪枝是一种常用技术，可有效减少内存占用、算术运算数量，从而减少推理时间。最近的修剪方法还考虑了 CNN 部署的目标设备（即图形处理单元），以减少实际的推理时间。然而，简单的度量，例如\(\ell ^1\)范数，用于决定要修剪哪些过滤器。在这项工作中，我们提出了一种硬件感知技术来探索可能的滤波器修剪配置的巨大多目标设计空间。我们的方法不仅结合了目标设备，还结合了可解释的人工智能技术，用于排名和决定要修剪哪些过滤器。对于每一层，要优化要修剪的滤波器数量，目的是最小化 CNN 的推理时间和错误率。实验结果表明，与最先进的方法相比，我们的方法可以将 CIFAR-10 数据集上的 VGG-16 和 ILSVRC-2012 数据集上的 ResNet-18 的推理时间分别加快 1.40 倍和 1.30 倍ABCP 鲁纳。