Dustin Tran

hi @elhamazizi. The answer is an unfortunate no. I believe there's a truncated DP model if you search the Forum. But we never got efficient inference to work on it(?).

You can try submitting a feature request for that in TF's Github issues. > On Feb 16, 2018, at 10:17 AM, elhamazizi wrote: > > Hi Dustin, > > Thanks,...

Have you uncollapsed the iteration cell? IIRC it should be within iteration's scope. (At the least, it must exist somewhere in the graph.)

Oh, I see. From that screenshot, it looks like inference appears across various places in the graph: iteration, the stack ops, strided slice, etc. None of those appear in your...

Nope. You are correct. Happy to take a contribution changing the number of iterations to one where it stabilizes.

It seems unnecessary to be super-specific about the number of training iterations if it takes that long. Maybe try larger batch sizes (e.g., 256) and a non-trivial latent dimension (e.g.,...

Thanks for sharing. Is this something that should be fixed in the code base? It seems like the inputs to `evaluate` should just have compatible dtype.

Can you provide a minimal reproducible example? What happens if you downcast the NumPy array to float32?

yeah that would be great to have. we have operator vi in a separate code base (https://arxiv.org/abs/1610.09033), which is very related; we're hoping to merge operator vi in soon. in...

Jogging my memory, this falls into what @matthewdhoffman and I call "stochastic graph optimization"—calling back to Theano's deterministic graph optimization. Namely, stochastic graph optimization boils down to defining a probabilistic...