Convolutional Neural Networks (CNNs) have a large number of parameters and take significantly large hardware resources to compute, so edge devices struggle to run high-level networks. This paper proposes a novel method to reduce the parameters and FLOPs for computational efficiency in deep learning models. We introduce accuracy and efficiency coefficients to control the trade-off between the accuracy of the network and its computing efficiency. The proposed Rewarded meta-pruning algorithm trains a network to generate weights for a pruned model chosen based on the approximate parameters of the final model by controlling the interactions using a reward function. The reward function allows more control over the metrics of the final pruned model. Extensive experiments demonstrate superior performances of the proposed method over the state-of-the-art methods in pruning ResNet-50, MobileNetV1, and MobileNetV2 networks.

翻译：卷积神经网络（CNN）拥有大量参数并在计算过程中消耗显著硬件资源，导致边缘设备难以运行高级网络。本文提出一种新颖方法，旨在减少深度学习模型的参数和浮点运算次数（FLOPs），以提升计算效率。我们引入准确性和效率系数，用于控制网络精度与计算效率之间的权衡。所提出的奖励元剪枝算法通过学习生成适用于剪枝模型的权重，该模型根据最终模型的近似参数进行选择，并通过奖励函数控制交互过程。奖励函数能够对最终剪枝模型的性能指标实现更精细的调控。大量实验表明，在ResNet-50、MobileNetV1和MobileNetV2网络的剪枝任务中，本方法性能优于现有最先进方法。