probability

probability copied to clipboard

Hi, I'm trying to sample from a Wishart distribution using `tfp.substrates.jax` and run into nans. I'm not sure why. Here's code to reproduce the error: ``` import jax.numpy as jnp...

saraelshawa

Can a tensorflow probability model be converted into tflite format for mobile prediction?

2

I have a TensorFlow probability model which I want to deploy on mobile devices. How can I do that?

maxkaustav

Remove `Variational Autoencoder` example which was based on Tensorflow Estimator and it is being deprecated for new usage.

chunduriv

Hello, I am replicating the pymc3 example [Bayesian Estimation Supersedes the T-Test](https://docs.pymc.io/en/v3/pymc-examples/examples/case_studies/BEST.html). I am using tensorflow==2.10.1 and tensorflow-probability==0.17.0. As a TFP example, I am following the tutorial [Gaussian Process Regression](https://www.tensorflow.org/probability/examples/Gaussian_Process_Regression_In_TFP)....

charles-crawford

Errors related to `name` argument in tfp.sts package

1

Hi, thank you for providing a great product. I'm trying to build a model with `tfp.sts` package but I'm facing issues around the `name` argument. ## `TypeError: tensorflow_probability.python.sts.components.autoregressive.AutoregressiveStateSpaceModel() got multiple...

hiroara

Hello everybody, following the [CONTRIBUTING](https://github.com/tensorflow/probability/blob/main/CONTRIBUTING.md) guidelines I first open this issue for the opportunity to discuss my proposed contribution. To familiarize myself with TensorFlow Probability and Probabilistic Modelling in general...

JannisZeller

Add sdist tar creation when running setup.py

1

Besides creating a `wheel` package, we enable the creation of a `sdist` package alongside it. This change only modifies the shell script used to automate the execution of `setup.py`, and...

hgonzale-li

I tried to convert [pointnet model](https://keras.io/examples/vision/pointnet/)(https://keras.io/examples/vision/pointnet/) to tensorflow probability model, but the results of the training were less than ideal. Can anyone help on this?

kuangzy2011

Hi, I am having troubles understanding why I am getting nan when stacking a bunch of conditional MAFs but I am not getting a nan with a single conditional MAF....

mtsatsev

There are two exclusive parameters in tfp.math.psd_kernels.RationalQuadratic. The first is `length_scale`, and the second is `inverse_length_scale`. But both are marked as preferred -- it is the default value in the...

tumpji