[5.1 二维卷积层](5.1%E4%BA%8C%E7%BB%B4%E5%8D%B7%E7%A7%AF%E5%B1%82.md) [5.2 填充和步幅](5.2%E5%A1%AB%E5%85%85%E5%92%8C%E6%AD%A5%E5%B9%85.md) [5.3 多输入通道和多输出通道](5.3%E5%A4%9A%E8%BE%93%E5%85%A5%E9%80%9A%E9%81%93%E5%92%8C%E5%A4%9A%E8%BE%93%E5%87%BA%E9%80%9A%E9%81%93.md) [5.4 池化层](5.4%E6%B1%A0%E5%8C%96%E5%B1%82.md) [5.5 卷积神经网络（LeNet）](5.5%E5%8D%B7%E7%A7%AF%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C.md) [5.6 深度卷积神经网络（AlexNet）](5.6%E6%B7%B1%E5%BA%A6%E5%8D%B7%E7%A7%AF%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C.md) [5.7 使用重复元素的网络(VGG)](5.7%E4%BD%BF%E7%94%A8%E9%87%8D%E5%A4%8D%E5%85%83%E7%B4%A0%E7%9A%84%E7%BD%91%E7%BB%9CVGG.md) [5.8 网络中的网络（NiN）](5.8%E7%BD%91%E7%BB%9C%E4%B8%AD%E7%9A%84%E7%BD%91%E7%BB%9C%EF%BC%88NiN%EF%BC%89.md) [5.9 含并行连结的网络（GoogLeNet）](5.9%E5%90%AB%E5%B9%B6%E8%A1%8C%E8%BF%9E%E7%BB%93%E7%9A%84%E7%BD%91%E7%BB%9C%EF%BC%88GoogLeNet%EF%BC%89.md) [5.10 批量归一化](5.10%E6%89%B9%E9%87%8F%E5%BD%92%E4%B8%80%E5%8C%96.md) [5.11 残差网络（ResNet）](5.11%E6%AE%8B%E5%B7%AE%E7%BD%91%E7%BB%9C%EF%BC%88ResNet%EF%BC%89.md) [5.12 稠密连接网络（DenseNet）](5.12%E7%A8%A0%E5%AF%86%E8%BF%9E%E6%8E%A5%E7%BD%91%E7%BB%9C.md)