您可以手动设置Tensorflow LSTM权重吗? [英] Can you manually set Tensorflow LSTM weights?
本文介绍了您可以手动设置Tensorflow LSTM权重吗?的处理方法，对大家解决问题具有一定的参考价值，需要的朋友们下面随着小编来一起学习吧！
问题描述
我正在探索使用递归神经网络来解决无人监督的问题.我需要分别设置每个门的权重.有什么办法可以做到吗?有这样的东西吗?
I'm exploring using recurrent neural networks to work on unsupervised problems. I would need to set the weights for each gate individually. Is there any way I can do so? Is there anything like this?
LSTMCell.Weights['Forget'] = ForgetGateWeights
推荐答案
在Tensorflow的问题部分中提出了类似的问题.查看此讨论 https://github.com/tensorflow/tensorflow/issues/3115 .
Similar question was raised in the issues section in tensorflow. Checkout this discussion https://github.com/tensorflow/tensorflow/issues/3115.
这篇关于您可以手动设置Tensorflow LSTM权重吗?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
查看全文
