Shiou-Ling Rene Wang

It looks like the code behavior depending on how the model is compiled: If you pass function object, then the keras code will prepend "binary" to the key. ``` model.compile(optimizer=optimizers.RMSprop(lr=0.001),...

in package __init__.py line 20 `from .fmin import fmin` might introduce name shadow and see fmin as function object instead of module A quick and dirty fix, I commented out...