论文标题
边缘设备中卷积神经网络的性能预测
Performance Prediction for Convolutional Neural Networks in Edge Devices
论文作者
论文摘要
在数据源附近的边缘设备上运行基于卷积神经网络（CNN）的应用程序可以满足延迟和隐私挑战。但是，由于它们减少的计算资源及其能量限制，这些边缘设备几乎无法满足CNN处理和数据存储的需求。对于这些平台，在精度和执行时间之间以最佳的权衡选择CNN，同时尊重硬件约束至关重要。在本文中，我们介绍并比较了基于机器学习的五（5）个，用于在两个（2）个边缘GPU平台上执行CNN的执行时间预测。对于这5种方法，我们还探讨了他们训练所需的时间并调整相应的超参数。最后，我们比较时间以在不同平台上运行预测模型。这些方法的利用将通过快速在目标边缘GPU上提供最佳的CNN来高度促进设计空间探索。实验结果表明，即使对于未探索和看不见的CNN模型的体系结构，极端梯度提升（XGBoost）的平均预测误差也不到14.73％。随机森林（RF）描绘了可比的准确性，但需要更多的精力和时间才能接受培训。对于CNN性能估计，其他3种方法（OLS，MLP和SVR）的准确性较低。
Running Convolutional Neural Network (CNN) based applications on edge devices near the source of data can meet the latency and privacy challenges. However due to their reduced computing resources and their energy constraints, these edge devices can hardly satisfy CNN needs in processing and data storage. For these platforms, choosing the CNN with the best trade-off between accuracy and execution time while respecting Hardware constraints is crucial. In this paper, we present and compare five (5) of the widely used Machine Learning based methods for execution time prediction of CNNs on two (2) edge GPU platforms. For these 5 methods, we also explore the time needed for their training and tuning their corresponding hyperparameters. Finally, we compare times to run the prediction models on different platforms. The utilization of these methods will highly facilitate design space exploration by providing quickly the best CNN on a target edge GPU. Experimental results show that eXtreme Gradient Boosting (XGBoost) provides a less than 14.73% average prediction error even for unexplored and unseen CNN models' architectures. Random Forest (RF) depicts comparable accuracy but needs more effort and time to be trained. The other 3 approaches (OLS, MLP and SVR) are less accurate for CNN performances estimation.
