probability

probability copied to clipboard

Any plans to update the examples to TensorFlow 2?

8

The examples in https://github.com/tensorflow/probability/tree/master/tensorflow_probability/examples do not run with TensorFlow 2, but it's been a while the stable TF2 is available. So, any plans to update the examples to TensorFlow 2...

nbro

Scaled Dirichlet does not integrate to 1

1

I am not sure if it should, but when I scale a Dirichlet non-homogeneously, it seems to no longer integrate to 1: ```python import numpy as np import tensorflow_probability as...

ricardoV94

New distribution: Skew-generalized Normal distribution

33

This pull request adds a new distribution, the generalized normal distribution variant 2, as defined on Wikipedia: https://en.wikipedia.org/wiki/Generalized_normal_distribution This variant generalizes the Gaussian with a new parameter, the peak or...

inhandan

hi, i was experimenting with tensorflow probability and i made a simple multilayer perceptron with 3 hidden layers alternated to 3 dropout layers and a final distributional layer that model...

pasq-cat

Speed up and tune VQ-VAE hyperparameters for Hugo's binarized MNIST

1

Currently, Hugo's binarized MNIST is slower and doesn't match the performance of MNIST thresholded at 0.5 in the VQ-VAE example. We should understand why this is happening and tune hyperparameters.

keyonvafa

tfp.stats.histogram cannot be compiled by XLA?

1

# Summary of problem Applying tfp.stats.histogram on the data in a tf keras model breaks XLA compilation. The example code (see below) works on CPU/GPU but with TPU strategy raises:...

yellowdolphin

TensorFlow v2.14.0 breaks TensorFlow Probability at import

9

## Summary of problem Today's release of [TensorFlow `v2.14.0`](https://github.com/tensorflow/tensorflow/releases/tag/v2.14.0) breaks TensorFlow Probability at import. In a fresh Python 3.11 virtual environment, installation of `tensorflow` `v2.14.0` and `tensorflow-probability` `v0.21.0` causes a...

matthewfeickert

Implementation of mean in categorical

1

> NotImplementedError: mean is not implemented: Categorical Defined a _mean method for implementing the mean of the Categorical distribution, following a previous PR (https://github.com/tensorflow/probability/pull/1411).

fotisdr

DeprecationWarning: distutils Version classes are deprecated

4

Very minor issue but when using the most recent version 0.19.0 I get this error > /tensorflow_probability/python/__init__.py:57: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead. if (distutils.version.LooseVersion(tf.__version__) <

elliottower

PoissonLogNormalQuadratureCompound parameterization doesn't match LogNormal parameterization

5

What are loc and scale in this distribution. Consider this: ``` import tensorflow_probability as tfp import numpy as np tfd = tfp.distributions loc = 2.4 scale = 0.8 d1 =...

pekaalto