/pkg/t/tensorflow-probability/tensorflow-probability-banner.webp

tensorflow-probability 0.24.0

Probabilistic modeling and statistical inference in TensorFlow

08-08-2021 268 words 2 minutes 0 views

Contents

Probabilistic modeling and statistical inference in TensorFlow

Stars: 4124, Watchers: 4124, Forks: 1073, Open Issues: 668

The tensorflow/probability repo was created 6 years ago and the last code push was 20 hours ago.
The project is very popular with an impressive 4124 github stars!

How to Install tensorflow-probability

You can install tensorflow-probability using pip

pip install tensorflow-probability

or add it to a project with poetry

poetry add tensorflow-probability

Package Details

Author: Google LLC
License: Apache 2.0
Homepage: http://github.com/tensorflow/probability
PyPi:: https://pypi.org/project/tensorflow-probability/
GitHub Repo:: https://github.com/tensorflow/probability

Classifiers

Scientific/Engineering
Scientific/Engineering/Artificial Intelligence
Scientific/Engineering/Mathematics
Software Development
Software Development/Libraries
Software Development/Libraries/Python Modules

No tensorflow-probability pypi packages just yet.

Errors

A list of common tensorflow-probability errors.

Code Examples

Here are some tensorflow-probability code examples and snippets.

GitHub Issues

The tensorflow-probability package has 668 open issues on GitHub

Please run in eager mode or implement the compute_output_shape method on your layer (DenseVariational).
Tensorflow Probability Glow has duplicated variable names
NotImplementedError with tensorflow_probability.layers.IndependentNormal
Bayesian CNN keeps giving the same output regardless of the input
Dimensions mismatch error when using fit_surrogate_posterior() with sample_size > 1
Optimize _kl_matrix_normal_matrix_normal for tfd.MatrixNormalLinearOperator
Optimal way to run multiple chains for a bayesian neural network trained with HMC (tfp.mcmc.HamiltonianMonteCarlo)
Feature request: Allow passing in scope for TransformedVariable, DeferredTensor for distributed programming
Feature Request: Serialization/deserialization for Distribution class objects
[Bug] Pivoted cholesky jit error when using jax backend
generalized gamma distribution
What would be a good way to get sample mean of joint distribution?
AttributeError: 'UserRegisteredTypeKerasTensor' object has no attribute 'mean' error raised.
module 'keras.utils.generic_utils' has no attribute 'populate_dict_with_module_objects'
Input initial_level_prior inconsistent with initial_state_prior (sts.LocalLevel)

See more issues on GitHub

Related Packages & Articles

keras 3.2.0

Keras is a deep learning API written in Python, running on top of the machine learning platform TensorFlow. The core data structures of Keras are layers and models. The philosophy is to keep simple things simple, while allowing the user to be fully in control when they need to (the ultimate control being the easy extensibility of the source code via subclassing).