Exécution de notre outil de synthèse sur un nouvel article
Vérifiez l’article ci-dessous, puis lancez sa synthèse.
Effects of Gradient Optimizer on Model Pruning
Yang Zhang (National University of Defense Technology, State Key Laboratory of Pulsed Power Laser Technology), Bin B. Zhu (National University of Defense Technology, State Key Laboratory of Pulsed Power Laser Technology), Qi Ma (National University of Defense Technology, State Key Laboratory of Pulsed Power Laser Technology), Huanan Wang
Résumé : Abstract Deep convolutional neural networks deploy in applications are hindered by their large parameters and high computational cost. In this paper, we test different gradient optimizer’s effect on YOLOv3 model pruning. This is achieved by enforcing channel-level sparsity in YOLOv3 network. The model trained with Adam optimizer get 5× reduction in model size only after training 60 epochs.