Abstract
Machine learning algorithms have been widely used in various applications and domains. To make the machine learning model suitable for different problems, it is necessary to optimize its hyper-parameters. Traditionally manual optimization is complex and time-consuming, hence many methods of automatic hyper-parameter optimization (HPO) have been proposed. In this work, we evaluate the performance of three typical HPO algorithms, including Random Search (RS), Tree-structured Parzen Estimator (TPE), and Covariance Matrix Adaptation Evolution Strategy (CMA-ES), with Median pruner and Hyperband pruner, on YOLOv5s on NWPU VHR-10 dataset. We demonstrate, that TPE shows the best performance. CMA-ES is the most effective in terms of consistent optimization. Using pruner can usually accelerate the process of HPO greatly with a little drop in accuracy. The model achieves 93.3% mAP in our task, which is usable in real applications.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
