OnceNAS: Discovering efficient on-device inference neural networks for edge devices

Yusen Zhang, Yunchuan Qin, Yufeng Zhang, Xu Zhou, Songlei Jian, Yusong Tan, Kenli Li

Abstract: Highlights•Carefully Selected Optimization Objectives: We choose hardware-agnostic objectives to control the model complexity.•Efficient Neural Architecture Search Strategy: We introduce a novel NAS method for resource-constrained edge devices.•Accurate Architecture Performance Evaluation: We propose an efficient neural architecture performance evaluation method.•Dataset Contribution: We contribute DARTS-Bench, including corresponding runtime information and API functions.