Play and Prune: Adaptive Filter Pruning for Deep Model Compression

05/11/2019
by   Pravendra Singh, et al.
0

While convolutional neural networks (CNN) have achieved impressive performance on various classification/recognition tasks, they typically consist of a massive number of parameters. This results in significant memory requirement as well as computational overheads. Consequently, there is a growing need for filter-level pruning approaches for compressing CNN based models that not only reduce the total number of parameters but reduce the overall computation as well. We present a new min-max framework for filter-level pruning of CNNs. Our framework, called Play and Prune (PP), jointly prunes and fine-tunes CNN model parameters, with an adaptive pruning rate, while maintaining the model's predictive performance. Our framework consists of two modules: (1) An adaptive filter pruning (AFP) module, which minimizes the number of filters in the model; and (2) A pruning rate controller (PRC) module, which maximizes the accuracy during pruning. Moreover, unlike most previous approaches, our approach allows directly specifying the desired error tolerance instead of pruning level. Our compressed models can be deployed at run-time, without requiring any special libraries or hardware. Our approach reduces the number of parameters of VGG-16 by an impressive factor of 17.5X, and number of FLOPS by 6.43X, with no loss of accuracy, significantly outperforming other state-of-the-art filter pruning methods.

READ FULL TEXT

page 5

page 6

research
11/20/2018

Stability Based Filter Pruning for Accelerating Deep CNNs

Convolutional neural networks (CNN) have achieved impressive performance...
research
08/31/2016

Pruning Filters for Efficient ConvNets

The success of CNNs in various applications is accompanied by a signific...
research
06/25/2019

COP: Customized Deep Model Compression via Regularized Correlation-Based Filter-Level Pruning

Neural network compression empowers the effective yet unwieldy deep conv...
research
09/30/2021

Deep Neural Compression Via Concurrent Pruning and Self-Distillation

Pruning aims to reduce the number of parameters while maintaining perfor...
research
07/20/2017

ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression

We propose an efficient and unified framework, namely ThiNet, to simulta...
research
06/08/2020

Novel Adaptive Binary Search Strategy-First Hybrid Pyramid- and Clustering-Based CNN Filter Pruning Method without Parameters Setting

Pruning redundant filters in CNN models has received growing attention. ...
research
06/14/2018

SCSP: Spectral Clustering Filter Pruning with Soft Self-adaption Manners

Deep Convolutional Neural Networks (CNN) has achieved significant succes...

Please sign up or login with your details

Forgot password? Click here to reset