Home Page
About Us


Keras is a neural network library providing a high-level API in Python and R


Theano is a numerical computation library for Python



Should i be surprised that the keras theano backend is about 18x - 19x slower than the keras tensorflow backend

from question  

Should Keras with Theano backend be over 18X slower than with Tensorflow backend?

I would recommend using theano binary lstm link or keras tutorial for this because their are fairly simple to understand and are well documented

from question  

How to prepare a dataset for speech recognition

Theano has low-level primitives to build machine learning models and on itself does not define any layers or optimizers and you would usually use it with some deep-learning library such as lasagne or keras while mxnet is higher level;so fare comparison would be mxnet vs keras not mxnet vs theano

from question  

MXNET vs Theano Experience

Back to Home
Data comes from Stack Exchange with CC-BY-SA-4.0