[英]How load multiple weight for some layers in keras?
I wanna Train network contain multiple (two and more) parallel CNN which common in last full connected layers, but i want use transfer learning method to train this networks separately at first and then merge them and fine tune my network.我想训练网络包含多个(两个或更多)并行 CNN,它们在最后一个全连接层中很常见,但我想使用迁移学习方法首先单独训练这些网络,然后合并它们并微调我的网络。
How I Can Do It by Keras
? Keras
如何做到这一点?
This is exactly what you need: Transfering weights from one layer to another这正是您所需要的: 将权重从一层转移到另一层
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.