-
dear authors, thanks for this package. I am wondering if Markov random field can be implemented using zhusuan, is so, do you have a tutorial for me to go through? thank you.
-
`out = tf.contrib.distributions.RelaxedOneHotCategorical(0.1,probs=out)`
-
Hey TF,
Is there some sort of multinomial function that can handle batches? When generating content, it is incredibly useful to introduce variance by 'rolling a dice'. I searched extensively in the d…
-
I'm using Gumbel-Softmax trick, that is I need to compute:
`softmax(-log(-log(uniform(0, 1))))`
In Tenserflow,
running `tf.nn.softmax(-tf.log(-tf.log(tf.uniform(...))))` is fine.
But in Pytorch,
…
-
Hi,
I've been trying to add Gumbel noise as in [here](https://github.com/Kaixhin/Autoencoders/blob/master/models/CatVAE.lua#L24), but no success.
Looks like several modules are still missing (e.g.…
-
Hi, I use TensorFlow 1.1.0 without gpu in mac osx 10.12.3 to test
`gumbel_softmax_vae_v2.ipynb`
I use ipython to run the code line by line, the error occurs in defining `logits_y`.
Hard to find i…
-
Hi,
Yesterday I reread the paper. I woke up thinking that the `logit-type` formulation is similar to the `softmax` normalization. I am a little surprised the comparison was not in the paper.
Thi…
-
I was playing around with the notebook, trying to look at the intermediate representations of the training data. I was expecting that the output of the `y` layer would be (pretty) sparse and (nearly)…
-
Get help from Ben on setting up the include-what-you-use tool, then listen to it.
-
These need a complete review. When I was looking through them, I realized that some of them were not testing all the possible combination of int, double and var for compilation.
Example: `function…