lenet

Gradient-Based learning Applied to Document Recognition Lenet的网络结构 对S2到C3层的说明： 如下图所示，C3的前6个feature map分别对应S2的三个连续的feature map; C3的6个feature map分别对应S2的4个连续的feature map;C3的3个feature map分别对应S2的4个间隔的featu

>>阅读原文<<