A slim tensorflow wrapper that provides syntactic sugar for tensor variables. This library will be helpful for practical deep learning researchers not beginners.
This fixes a bug where tf.sg_summary_activation is called if the variable_scope was in reuse mode because of the parent scope and not because reuse=True was set.
This fixes a bug where
tf.sg_summary_activation
is called if thevariable_scope
was in reuse mode because of the parent scope and not becausereuse=True
was set.I wanted to add a test case but I'm not sure where to put it, I put it in a gist for now (https://gist.github.com/AndreasMadsen/5eb010f998f8d1eb54d23c6c33294301).