ResNet经过残差学习解决了深度网络的退化问题,让咱们能够训练出更深的网络,这称得上是深度网络的一个历史大突破吧。也许不久会有更好的方式来训练更深的网络,让咱们一块儿期待吧! 目前,您能够在人工智能建模平台 Mo 找到基于tensorflow 的34层的残差网络(ResNet)实现样例,数据集是CIFAR-10 (CIFAR的十分类数据集),这个样例在测试集上的精度为90%,验证集上的精度为98%。主程序在ResNet_Operator.py中,网络的Block结构在ResNet_Block.py中,训练完的模型保存在results文件夹中。 项目源码地址:momodel.cn/explore/5d1…
参考文献: [1] K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. arXiv preprint arXiv:1512.03385,2015. [2] Y. LeCun, L. Bottou, G. B. Orr, and K.-R.M¨uller. Efficient backprop.In Neural Networks: Tricks of the Trade, pages 9–50. Springer, 1998. [3] X. Glorot and Y. Bengio. Understanding the difficulty of training deep feedforward neural networks. In AISTATS, 2010. [4] A. M. Saxe, J. L. McClelland, and S. Ganguli. Exact solutions to the nonlinear dynamics of learning in deep linear neural networks.arXiv:1312.6120, 2013. [5] K. He, X. Zhang, S. Ren, and J. Sun. Delving deep into rectifiers:Surpassing human-level performance on imagenet classification. In ICCV, 2015. [6] S. Ioffe and C. Szegedy. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In ICML, 2015. 网络