probability

probability copied to clipboard

The current behaviour for `tensorflow_probability.bijectors.Bijector` is to cache the input to be used if the inverse function is called. I would very much like a keyword being able to turn...

alexhepburn

Categorical features in logistic regression

5

Hi, I'm following the logistic regression example ([https://github.com/tensorflow/probability/blob/master/tensorflow_probability/examples/logistic_regression.py](logistic_regression.py)) and trying to implement it with some real life data that has a mixture of numerical and categorical variables. Each of my...

allenchng

improve text and visuals in Bayesian Gaussian mixture model tutorial

3

See also http://edwardlib.org/tutorials/unsupervised.

dustinvtran

Tutorial on Variational Inference

6

The current tutorials cover a majority of MCMC. Could we get one for variational inference? The edward tutorial on Supervised Learning shows how to run inference using Kullback-Leibler divergence. It...

nishantb21

How to save and load trained trainable_variables in tensorflow probability distribution?

5

I want to build a flow model which I can save the trained model. ``` flow = tfd.TransformedDistribution( ... distribution=tfd.Normal(loc=0.0, scale=1.0), bijector=my_bijectors ) for e in epochs: ... with tf.GradientTape()...

moonman925

Have I written custom code (as opposed to using a stock example script provided in TensorFlow): No OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Ubuntu 18.04 TensorFlow installed from...

markm541374

Optimal way to run multiple chains for a bayesian neural network trained with HMC (tfp.mcmc.HamiltonianMonteCarlo)

5

Hi, I'm working on a master's thesis where we want to sample the exact posterior of a bayesian neural network using HMC and the No-U-Turn sampler in regression tasks. The...

reneaas

Memory leak with tfb.Glow ?

9

Info:` tf-nightly-gpu` and `tfp-nightly` , code tested on single tesla v100, ubuntu, cuda11.0, cudnn8 RAM grows linearly when training a `tfb.Glow` based `tfd.TransformedDistribution`. It takes 16G when it starts training...

gitlabspy

Cannot train tfb.Glow with tf.keras ?

1

Hi, I am getting NaNs when I sample images after training the glow bijector. Is there some compatibility issue between tf and tfp, or am I doing something wrong? ```...

khanx169

NotImplementedError with tensorflow_probability.layers.IndependentNormal

5

Please see MWE below. The code gives a NotImplementedError after `outputs = tfpl.IndependentNormal(event_shape = encoded_shape) (layer3)`. The model, however, is constructed correctly. This issue was originally raised in the corresponding...

anirban-mukherjee