Hi! Is project Edward still being maintained, or has dev work shifted to Edward2?
Also, should this forum be used for questions about Edward2 or should that occur elsewhere (e.g.
Let me know if any help is wanted migrating the examples. It would be great for the community to have these examples work with the latest version of TensorFlow and Edward2. (It’d also be a good learning exercise for me
Thanks for the guidance,
Unfortunately no re:maintenance. I have my hands tied across quite a few systems and research projects. I recommend TF’s stack overflow and
When the NIPS camera-ready for Edward2 is released, more details should be available. In the meantime, there’s documentation here:
This file has been truncated.
Edward2 is a probabilistic programming language in TensorFlow and Python. It
extends the TensorFlow ecosystem so that one can declare models as
probabilistic programs and manipulate a model's computation for flexible
training, latent variable inference, and predictions.
Are you upgrading from Edward? Check out the guide
## 1. Models as Probabilistic Programs
### Random Variables
In Edward2, we use
to specify a probabilistic model's structure.
A random variable `rv` carries a probability distribution (`rv.distribution`),
which is a TensorFlow Distribution instance governing the random variable's methods
such as `log_prob` and `sample`.
Thanks for the reply, Dustin!
What scope will be covered by the paper? Anything beyond what’s here, ported?