LB-CNN: An Open Source Framework for Fast Training of Light Binary Convolutional Neural Networks using Chainer and Cupy

TL;DR

This paper introduces LB-CNN, a fast training framework for light binary CNNs optimized for low-energy platforms, demonstrating high accuracy and efficiency on multiple datasets, suitable for industrial image recognition tasks.

Contribution

The paper presents an open-source framework using Chainer and Cupy for rapid training of LB-CNNs, enabling deployment on low-energy devices with high accuracy.

Findings

Achieved up to 100% accuracy on face recognition datasets.

Demonstrated significant speed-ups in training using Chainer/Cupy.

Provided a versatile framework compatible with cloud platforms and various deployment tools.

Abstract

Light binary convolutional neural networks (LB-CNN) are particularly useful when implemented in low-energy computing platforms as required in many industrial applications. Herein, a framework for optimizing compact LB-CNN is introduced and its effectiveness is evaluated. The framework is freely available and may run on free-access cloud platforms, thus requiring no major investments. The optimized model is saved in the standardized .h5 format and can be used as input to specialized tools for further deployment into specific technologies, thus enabling the rapid development of various intelligent image sensors. The main ingredient in accelerating the optimization of our model, particularly the selection of binary convolution kernels, is the Chainer/Cupy machine learning library offering significant speed-ups for training the output layer as an extreme-learning machine. Additional training of the output layer using Keras/Tensorflow is included, as it allows an increase in accuracy. Results for widely used datasets including MNIST, GTSRB, ORL, VGG show very good compromise between accuracy and complexity. Particularly, for face recognition problems a carefully optimized LB-CNN model provides up to 100% accuracies. Such TinyML solutions are well suited for industrial applications requiring image recognition with low energy consumption.