介绍关于空洞卷积的理论可以查看以下链接,这里我们不详细讲理论: 1.Long J, Shelhamer E, Darrell T, et al. Fully convolutional networks for semantic segmentation[C]. Computer Vision and Pattern Recognition, 2015. 2.Yu, Fisher, and Vladlen Koltun. “Multi-scale context aggregation by d
Convolutional Neural Networks: Step by Step implement convolutional (CONV) and pooling (POOL) layers in numpy, including both forward propagation and (optionally) backward propagation. Notation: Superscript \([l]\) denotes an object of the \(l^{th}\)
Google Inception Net,ILSVRC 2014比赛第一名.控制计算量.参数量,分类性能非常好.V1,top-5错误率6.67%,22层,15亿次浮点运算,500万参数(AlexNet 6000万).V1降低参数量目的,参数越多模型越庞大,需数据量越大,高质量数据昂贵:参数越多,耗费计算资源越大.模型层数更深,表达能力更强,去除最后全连接层,用全局平均池化层(图片尺寸变1x1),参数大减,模型训练更快,减轻过拟合(<Network in Network>论文),Inceptio