Trying to put Tensorflow probability in my tool belt. Is it just me, or is Tensorflow incredibly verbose? What is the point of that? I could write a model and sample it in, apparently, half the number of lines using Stan or Pymc3.
-
-
Just read some Edward2 examples. Yea, I'll wait for Pymc4
-
Yeah, tensorflow is verbose. It's cause of how they do their auto-diff that's sorta like runtime compiled symbolic differentiation. Edward inherits this but also seems to be going in a more neural net variational big iron computing direction. Away from Stan/PyMC.
- 2 more 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.