Open AccessEffects of Gradient Optimizer on Model Pruning
Author(s) -
Yang Zhang,
Bin Zhu,
Qi Ma,
Huanan Wang
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/711/1/012095
Subject(s) - pruning , computer science , convolutional neural network , artificial intelligence , reduction (mathematics) , machine learning , artificial neural network , deep learning , algorithm , mathematics , agronomy , biology , geometry
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.