Data Science Stack Exchange is a question and answer site for Data science professionals, Machine Learning specialists, and those interested in learning more about the field. It only takes a minute to sign up.
Sign up to join this community
I am about to dive into a long NN research project and wanted a push in the direction of Pylearn2 or TensorFlow? As of Dec 2015 has the community started to lean one direction or another?
This link has given me concern about getting tied to TenserFlow.
You might want to take into consideration that Pylearn2 has no more developer, and now points to other Theano-based libraries:
There are other machine learning frameworks built on top of Theano that could interest you, such as: Blocks, Keras and Lasagne.
As Dawny33 says, TensorFlow is just getting started, but it is interesting to note that the number of questions on TensorFlow (244) on Stack Overflow already surpasses Torch (166) and will probably catch up with Theano (672) in 2016.
As far as I know, the existing (almost all) libraries in Python can handle very complex models of Neural Networks.
TensorFlow is however not polished as of now. It still has a long way to grow before getting accepted as a mainstream library for ML.
So, going ahead with the existing libraries like PyLearn/Keras/Torch, etc makes sense as of now (also as they have wide and dedicated communities already), as you need to concentrate on research rather than worrying on bugs and technical problems of a library.
