调参影响深度网络性能，实验发现maxpool+adam+tanh效果最佳
Impact of Tuning Parameters in Deep Convolutional Neural Network Using a Crack Image Dataset
- 用裂纹图像数据集测试卷积网络调参影响
- maxpool配合adam优化器和tanh激活函数表现最优
- 适合关注模型调参细节的深度学习实践者
分类器性能依赖于参数调优。本文研究了多种调参对深度卷积神经网络（DCNN）性能的影响。实验采用包含两层卷积层（CL）、两层池化层（PL）、一层丢弃层（Dropout）和一个全连接层的DCNN分类器，使用含两类（负/正）的裂纹图像数据集进行评估。结果表明，在使用maxpooling时，搭配adam优化器与tanh激活函数可使DCNN表现更优。
原文摘要 · Abstract (English)
The performance of a classifier depends on the tuning of its parame ters. In this paper, we have experimented the impact of various tuning parameters on the performance of a deep convolutional neural network (DCNN). In the ex perimental evaluation, we have considered a DCNN classifier that consists of 2 convolutional layers (CL), 2 pooling layers (PL), 1 dropout, and a dense layer. To observe the impact of pooling, activation function, and optimizer tuning pa rameters, we utilized a crack image dataset having two classes: negative and pos itive. The experimental results demonstrate that with the maxpooling, the DCNN demonstrates its better performance for adam optimizer and tanh activation func tion.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。