如何为 keras 中的某些层加载多个权重？
[英]How load multiple weight for some layers in keras?
问题描述
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？
1 个解决方案
解决方案1
0 2020-12-10 00:35:50
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.
相关问题
Keras 您正在尝试将包含 2 层的权重文件加载到具有 1 层的 model - Keras you are trying to load a weight file containing 2 layers into a model with 1 layers
Keras重量文件加载例外：将2层加载到具有0层的模型中 - Keras weight file load exception: loading 2 layers into a model with 0 layers
如何在两个 keras 层之间共享权重？ - How to share weight between two keras layers?
keras 加载模型错误，尝试将包含 17 层的权重文件加载到具有 0 层的模型中 - keras load model error trying to load a weight file containing 17 layers into a model with 0 layers
Keras尝试保存并加载模型错误您正在尝试将包含16层的权重文件加载到具有0层的模型中 - Keras try save and load model error You are trying to load a weight file containing 16 layers into a model with 0 layers
如何将数值作为权重导入Keras / Tensorflow层中？ - How to import numerical values as weight into the Keras/Tensorflow layers?
如何以张量形式访问clip_by_weight的Keras层中的权重变量？ - How to access weight variables in Keras layers in tensor form for clip_by_weight?
如何修复（“ValueError: You are trying to load a weight file contains 16 layers into a model with 0 layers”） - How to fix (“ValueError: You are trying to load a weight file containing 16 layers into a model with 0 layers”)
如何在keras中间层的结果之间进行一些计算 - How to do some calculation between the results from the middle layers in keras
如何排除层权重并仅保留我想要的权重并使用 keras 预测模型？ - How to excluded layers weight and only keep the weights I want and predict model by using keras?
相关标签