X-TrainCaps: Accelerated Training of Capsule Nets through Lightweight Software Optimizations

05/24/2019
by   Alberto Marchisio, et al.
0

Convolutional Neural Networks (CNNs) are extensively in use due to their excellent results in various machine learning (ML) tasks like image classification and object detection. Recently, Capsule Networks (CapsNets) have shown improved performances compared to the traditional CNNs, by encoding and preserving spatial relationships between the detected features in a better way. This is achieved through the so-called Capsules (i.e., groups of neurons) that encode both the instantiation probability and the spatial information. However, one of the major hurdles in the wide adoption of CapsNets is its gigantic training time, which is primarily due to the relatively higher complexity of its constituting elements. In this paper, we illustrate how can we devise new optimizations in the training process to achieve fast training of CapsNets, and if such optimizations affect the network accuracy or not. Towards this, we propose a novel framework "X-TrainCaps" that employs lightweight software-level optimizations, including a novel learning rate policy called WarmAdaBatch that jointly performs warm restarts and adaptive batch size, as well as weight sharing for capsule layers to reduce the hardware requirements of CapsNets by removing unused/redundant connections and capsules, while keeping high accuracy through tests of different learning rate policies and batch sizes. We demonstrate that one of the solutions generated by X-TrainCaps framework can achieve 58.6 accuracy improvement), compared to the CapsNet in the original paper by Sabour et al. (2017), while other Pareto-optimal solutions can be leveraged to realize trade-offs between training time and achieved accuracy.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/23/2019

1D-Convolutional Capsule Network for Hyperspectral Image Classification

Recently, convolutional neural networks (CNNs) have achieved excellent p...
research
06/24/2020

Accelerated Large Batch Optimization of BERT Pretraining in 54 minutes

BERT has recently attracted a lot of attention in natural language under...
research
03/10/2019

A Hybrid GA-PSO Method for Evolving Architecture and Short Connections of Deep Convolutional Neural Networks

Image classification is a difficult machine learning task, where Convolu...
research
10/16/2018

Approximate Fisher Information Matrix to Characterise the Training of Deep Neural Networks

In this paper, we introduce a novel methodology for characterising the p...
research
10/30/2020

Training EfficientNets at Supercomputer Scale: 83 Accuracy in One Hour

EfficientNets are a family of state-of-the-art image classification mode...
research
08/19/2020

NASCaps: A Framework for Neural Architecture Search to Optimize the Accuracy and Hardware Efficiency of Convolutional Capsule Networks

Deep Neural Networks (DNNs) have made significant improvements to reach ...

Please sign up or login with your details

Forgot password? Click here to reset