Add support for symbolic weight initialization with Pymc3

[gbengaoti]

Hi, I am trying to combine keras (theano backend) with Pymc3, I found that Keras does not support such weight initialization as Lasagne does. Is it possible to add support for symbolic initialization in keras?

#6546 - It is the same issue as mine. I also get the missing input error.

Here is a link to a github gist of the code:
https://gist.github.com/gbengaoti/ec88e36d3dd7f66d9bc32fcf8ec93d18

[tomcaputo]

+1

[stale]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed after 30 days if no further activity occurs, but feel free to re-open a closed issue if needed.