I am a newbie with Tensorflow. I used pymc3 for my project and heard Theano will stop developing, so I have to swing to Tensorflow and edward to implement Bayesian Deep learning. When I read Weight Uncertainty in Neural Networks , I planed to implement the Bayesian by Backpropagation algorithm they …

I can answer myself ^-^! First, I used tfdbg with filter has_inf_or_nan to debug the nan source. If the OS is Windows, there may be some problems. Second, I found the problem was stem from learning rate. So I modified the VI and KLqp file to enable directly setting learning rate. With smaller lear…

Loss are NaN when using KLqp or Bayesian by Backpropagation

YSanchezAraujo May 5, 2018, 8:29pm 3

hi @sejabs, could you provide information for how you reduced the learning rate through the edward api?

Topic		Replies	Views
Loss are NaN when using KLqp or Bayesian by Backpropagation	0	563	March 31, 2018
Several problems when implement Bayes by backprop using edward	0	561	March 30, 2018
Simple Hierarchical Distribution	2	1549	October 12, 2017
Nan in summary histogram for: gradient	2	4473	June 15, 2017
Beta binomial example	5	1875	August 14, 2017

Loss are NaN when using KLqp or Bayesian by Backpropagation

Related topics