75 questions per day on average -- you could employ a few people full time just answering them
Show this thread
Doing some data crunching. Graph: daily number of new StackOverflow questions that either contain one of {"keras", "tensorflow"} in their tags or titles, or one of {"torch", "pytorch", "torchvision"}. Past ~6 months.pic.twitter.com/H5uRT9NHYj
-
-
-
-
Now here's a really fascinating one. Weekly number of research papers indexed on arXiv specifically, and on all of Google Scholar (which includes arXiv), that mention TensorFlow, Keras, or PyTorch.pic.twitter.com/oVBsukcqXg
Show this thread -
This tells us two things: 1) The pure ML research community (posts on arXiv) is evenly split between TF and PyTorch 2) The broader scientific community interested in applying ML (doesn't post on arXiv; often doesn't even publish preprints), which is ~20x larger, uses TF/Keras
Show this thread
End of conversation
New conversation -
-
-
Which is which?
-
I'll assume this is a real question. The red curve is tensorflow | keras, the blue curve is torch | pytorch | torchvision. The smooth overlay is an exponential moving average of period 10.
- Show replies
New conversation -
-
-
Clearly one is more confusing than the other...
-
Just being cheeky btw ;) There's probably better explanations for this data
End of conversation
New conversation -
-
-
Legend please. It doesn't say which color line is for what.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
You can have a lot of fun looking a the tag data. https://minimaxir.com/2018/02/stack-overflow-questions/ …pic.twitter.com/8zYDikorXo
-
C people work at weekends?
- Show replies
New conversation -
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.