edward

edward copied to clipboard

I used seed as: ed.set_seed(1) ed.util.set_seed(1)

when I use: inference = ed.KLqp({z: qz}, data) inference.update()

the loss is different.

Hey @JhyOnya ! To let you know, this repo is no longer maintained. We still actively respond on the other relevant research codebases like https://github.com/google/edward2, https://github.com/tensorflow/probability, and https://github.com/google/uncertainty-baselines.