Adaptation of Deep Learning Models to Resource Constrained Edge Devices

Techniques for generating a set of Deep Learning (DL) models are described. An example method includes training an initial set of DL models using the training data, wherein a topology of each of the DL models is determined based on the parameters vector. The method also includes generating a set of estimate performance functions for each of the DL models in the initial set based on the set of edge-related metrics, and generating a plurality of objective functions based on the set of estimated performance functions. The method also includes generating a final DL model set based on the objectivefunctions, receiving a user selection of a selected DL model from the final DL model set, and deploying the selected DL model to an edge device. 描述了用于生成深度学习(DL)模型的集合的技术。示例方法包括使用训练数据来训练DL模型的初始集合，其中基于参数向量来确定DL模型中的每一个的拓扑。该方法还包括基于边缘相关度量的集合为初始集合中的DL模型中的每一个生成估计性能函数的集合，以及基于估计性能函数的集合生成多个目标函数。该方法还包括基于目标函数生成最终DL模型集合，接收对从最终DL模型集合中选择的DL模型的用户选择，并将所选择的DL模型部署到边缘设备。