深度学习框架Caffe在图像分类中的应用
发布时间：2019-06-15 18:48
【摘要】：2006年深度学习的提出为机器学习领域带来新的革命,深度学习的成功不仅依赖于理论和模型上的突破,也离不开大数据环境下的海量训练样本以及不断革新的先进计算技术。在GPU被应用于科学计算之前,神经网络特别是大型神经网络的训练时间往往令人生畏。GPU特别适应于并行计算的特性给神经网络的训练速度带来数十倍的提升。开源的GPU计算框架也不断地推陈出新,推动深度学习在各方面的应用,Caffe就是其中的一种。由于简单易用、性能强大,Caffe框架受到了广泛的认可。利用Caffe框架对印章类型进行识别,所采用的两种模型都取得极好的实验效果,对印章的自动识别提供新的参考。
[Abstract]:In 2006, the proposal of deep learning brought a new revolution to the field of machine learning. The success of deep learning not only depends on the breakthrough of theory and model, but also depends on the massive training samples and innovative advanced computing technology in big data environment. Before GPU was applied to scientific computing, the training time of neural network, especially large neural network, was often daunting. GPU is especially suitable for parallel computing, which brings dozens of times improvement to the training speed of neural network. Open source GPU computing framework is also constantly innovative, promoting in-depth learning in all aspects of the application, Caffe is one of them. Because of its simple and easy to use and powerful performance, Caffe framework has been widely recognized. The Caffe framework is used to identify the seal types, and the two models have achieved excellent experimental results, which provides a new reference for the automatic recognition of seals.
【作者单位】： 四川大学计算机学院;
【基金】：国家自然科学基金资助项目(61303015) 四川省科技计划项目(No.2014GZ0005-5)
【分类号】：TP391.41
本文编号：2500433
[Abstract]:In 2006, the proposal of deep learning brought a new revolution to the field of machine learning. The success of deep learning not only depends on the breakthrough of theory and model, but also depends on the massive training samples and innovative advanced computing technology in big data environment. Before GPU was applied to scientific computing, the training time of neural network, especially large neural network, was often daunting. GPU is especially suitable for parallel computing, which brings dozens of times improvement to the training speed of neural network. Open source GPU computing framework is also constantly innovative, promoting in-depth learning in all aspects of the application, Caffe is one of them. Because of its simple and easy to use and powerful performance, Caffe framework has been widely recognized. The Caffe framework is used to identify the seal types, and the two models have achieved excellent experimental results, which provides a new reference for the automatic recognition of seals.
【作者单位】： 四川大学计算机学院;
【基金】：国家自然科学基金资助项目(61303015) 四川省科技计划项目(No.2014GZ0005-5)
【分类号】：TP391.41
【参考文献】
相关硕士学位论文 前1条
1 尚利峰;脉冲耦合神经网络在图像处理中的应用[D];电子科技大学;2007年
【共引文献】
相关硕士学位论文 前2条
1 陈龙斌;基于脉冲耦合神经网络的图像分割与图像融合研究[D];云南大学;2015年
2 胡芳;脉冲耦合神经网络在图像分割和人脸检测中的应用研究[D];云南大学;2011年
，本文编号：2500433
本文链接：https://www.wllwen.com/kejilunwen/ruanjiangongchenglunwen/2500433.html
