论文标题
图像分类的Raspberry Pi上有效的卷积神经网络
Efficient Convolutional Neural Networks on Raspberry Pi for Image Classification
论文作者
论文摘要
通过在计算机视觉领域（CV）领域深度学习算法的良好性能，卷积神经网络（CNN）体系结构已成为计算机视觉任务的主要骨干。随着移动设备的广泛使用，基于具有低计算能力平台的神经网络模型逐渐引起人们的注意。但是，由于计算能力的限制，移动设备上通常无法使用深度学习算法。本文提出了轻巧的卷积神经网络TripLenet，可以在Raspberry Pi上轻松运行。从阈值中的块连接概念中采用，新提出的网络模型会压缩并加速网络模型，减少网络的参数量，并在确保准确性的同时缩短每个图像的推理时间。我们提出的TripLenet和其他最先进的（SOTA）神经网络在Raspberry Pi上使用CIFAR-10和SVHN数据集进行了图像分类实验。实验结果表明，与GhostNet，Mobilenet，Thehshnet，EfficityNet和HardNet相比，每个图像的推理时间分别缩短了15％，16％，17％，24％和30％。这项工作的详细代码可在https://github.com/ruiyangju/triplenet上找到。
With the good performance of deep learning algorithms in the field of computer vision (CV), the convolutional neural network (CNN) architecture has become a main backbone of the computer vision task. With the widespread use of mobile devices, neural network models based on platforms with low computing power are gradually being paid attention. However, due to the limitation of computing power, deep learning algorithms are usually not available on mobile devices. This paper proposes a lightweight convolutional neural network, TripleNet, which can operate easily on Raspberry Pi. Adopted from the concept of block connections in ThreshNet, the newly proposed network model compresses and accelerates the network model, reduces the amount of parameters of the network, and shortens the inference time of each image while ensuring the accuracy. Our proposed TripleNet and other state-of-the-art (SOTA) neural networks perform image classification experiments with the CIFAR-10 and SVHN datasets on Raspberry Pi. The experimental results show that, compared with GhostNet, MobileNet, ThreshNet, EfficientNet, and HarDNet, the inference time of TripleNet per image is shortened by 15%, 16%, 17%, 24%, and 30%, respectively. The detail codes of this work are available at https://github.com/RuiyangJu/TripleNet.
