Loading...

{{notif_text}}

SocialHelpouts is now CutShort! Read about it here
Who pays how much? Be informed with this salary report on Indian startups.
Why join channels?
Learn from peers
Discuss and share learning resources with the top professionals across the world
Open business or job opportunities
Earn reputation points to get consulting projects, attract talent or land jobs.
Accelerate your growth
Grow your network and get exclusive deals from our learning partners.
signup now
Manas Shrivastava asked a question

Why would you choose Tensor Flow over Theano?

  

answer
submitting answer...
submit
No answers yet. Be the first one to answer!
1 answer
VISHNU SUBRAMANIAN Deep learning researcher.
A year or two back theano was awesome. Even today there are use cases where theano is still good. But tensorflow comes with more advantages like
  1. A great community backed by Google.
  2. A lot of new additions to the framework in frequent intervals. It has become the most popular ML framework in Github.
  3. It has other components like Tensorflow serving layer , Tensorboard for visualizing the networks you build . Which is very useful in debugging. 

If you are just starting with deep learning , I would recommend you to try Keras. At present you can switch the backends to either theano or tensorflow . 
Loading comments...
To view all answers to this question, join this channel
join this channel
Awesome! You have connected your Facebook account. Like us on Facebook to stay updated.