18641

A Framework for Fast and Efficient Neural Network Compression

Hyeji Kim, Muhammad Umar Karim, Chong-Min Kyung
School of Electrical Engineering, KAIST, Republic of Korea
arXiv:1811.12781 [cs.CV], (4 Dec 2018)

@article{kim2018framework,

   title={A Framework for Fast and Efficient Neural Network Compression},

   author={Kim, Hyeji and Karim, Muhammad Umar and Kyung, Chong-Min},

   year={2018},

   month={nov},

   archivePrefix={"arXiv"},

   primaryClass={cs.CV}

}

Download Download (PDF)   View View   Source Source   

1772

views

Network compression reduces the computational complexity and memory consumption of deep neural networks by reducing the number of parameters. In SVD-based network compression, the right rank needs to be decided for every layer of the network. In this paper, we propose an efficient method for obtaining the rank configuration of the whole network. Unlike previous methods which consider each layer separately, our method considers the whole network to choose the right rank configuration. We propose novel accuracy metrics to represent the accuracy and complexity relationship for a given neural network. We use these metrics in a non-iterative fashion to obtain the right rank configuration which satisfies the constraints on FLOPs and memory while maintaining sufficient accuracy. Experiments show that our method provides better compromise between accuracy and computational complexity/memory consumption while performing compression at much higher speed. For VGG-16 our network can reduce the FLOPs by 25% and improve accuracy by 0.7% compared to the baseline, while requiring only 3 minutes on a CPU to search for the right rank configuration. Previously, similar results were achieved in 4 hours with 8 GPUs. The proposed method can be used for lossless compression of neural network as well. The better accuracy and complexity compromise, as well as the extremely fast speed of our method makes it suitable for neural network compression.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: