Make compatible with Keras 2

[LimKaiZhuo]

There are quite a few issues when using your code with Keras 2. For example, the customised Keras layers does not work and gives the following issue: File "C:\Users\User\Desktop\Python\SNN_cont_only\own_package\NGF\layers.py", line 397, in init super(NeuralGraphOutput, self).init(**kwargs) File "C:\Program Files (x86)\Python36-64\lib\site-packages\keras\engine\base_layer.py", line 128, in init raise TypeError('Keyword argument not understood:', kwarg) TypeError: ('Keyword argument not understood:', 'activation')

[tivaro]

Hi @LimKaiZhuo,

I haven't looked at this codebase in a while, but it seems that this fork contains a version that was modified by @iwatobipen to work for keras2 and tensorflow.

[tivaro]

@tevang

[tevang]

I tried @iwatobipen 's fork and I can verify that it works with Python 3.7.3, Keras-2.2.4, TensorFlow 1.13.1 (Theano is not needed any more). I have spent the last 3 days adapting the code to work with these latest versions, but it needed much more modifications than I expected. Thank you for pointing that fork out. I would like to become a co-developer and add a user-friendly API that will allow someone who is not an expert to use default network architectures and retrieve the molecules in feature vector form, suitable for training of any ML model.