Re:Introducing Keras 2
by evernflow on Tuesday March 14, 2017 @11:57PM
(#13873696)
This is surprising since keras basically started as a rip off of the Torch API in Python
[ Parent
| on HN ]
Re:Introducing Keras 2
by HelloNurse on Wednesday March 15, 2017 @04:31AM
(#13874649)
Layering Keras on top of another framework, such as Theano, is useful because it gains compatibility with code using that other framework.
If Keras and PyTorch are both similar (in spirit and API) to Torch, integrating PyTorch-based code as is into Keras project would be very low-value compared to a presumably easy translation to Keras.