TensorFlow is the platform of choice for deep learning in the research community. These are deep learning framework mentions on arXiv over the past 3 monthspic.twitter.com/v6ZEi63hzP
Show this thread
Keras usage is most dominant in the industry (both large companies and startups) and in the overall data science community. In the research community, Keras has a much smaller market share
-
-
-
Unfortunately I had to remove forks from the score, as they appear to be artificially inflated for TF. TF has 60k forks, growing at 10k/month, which doesn't make any sense. Possibly someone misusing the GitHub API...pic.twitter.com/eUSdXdtRo4
Show this thread
End of conversation
New conversation -
-
-
Context: Many DL practitioners in industry have been postgraduate researchers (MSc, PhD,…)pic.twitter.com/Xi1DMX3jcr
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I'm looking to stop bouncing between keras and TF and am only 6 months into ML. Are there clear advantages of any one or is it just familiarity/affinity? I lean toward TF because of exposure and support.
-
Haha. Nevermind. I think I know what Fancois will say. I will tell you, I feel Keras is more intuitive but worry that I will find TF is the industry standard. It is what everyone I've talked to asks for first.
End of conversation
New conversation -
-
-
My experience is, research in academics is more in a fundamental level and they end up creating some custom functions and layer equation with tf as background and so they migrate to TF altogether. But keras is no doubt best for rapid prototyping and hence in industry.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Currently using Tendorflow lite for dev on mobile and embedded devices. I am not sure if Keras is supported as well?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.