A Framework for Fast and Efficient Neural Network Compression
Authors:
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 4 references indexed in Scilit:
- Regularized Evolution for Image Classifier Architecture SearchProceedings of the AAAI Conference on Artificial Intelligence, 2019
- Accelerating Convolutional Networks via Global & Dynamic Filter Pruning2018
- ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression2017
- Speeding up Convolutional Neural Networks with Low Rank Expansions2014