Probabilistic modeling and statistical inference in TensorFlow
Project description
TensorFlow Probability
TensorFlow Probability is a library for probabilistic reasoning and statistical analysis in TensorFlow. As part of the TensorFlow ecosystem, TensorFlow Probability provides integration of probabilistic methods with deep networks, gradientbased inference via automatic differentiation, and scalability to large datasets and models via hardware acceleration (e.g., GPUs) and distributed computation.
Our probabilistic machine learning tools are structured as follows.
Layer 0: TensorFlow. Numerical operations. In particular, the LinearOperator
class enables matrixfree implementations that can exploit special structure
(diagonal, lowrank, etc.) for efficient computation. It is built and maintained
by the TensorFlow Probability team and is now part of
tf.linalg
in core TF.
Layer 1: Statistical Building Blocks
 Distributions (
tfp.distributions
): A large collection of probability distributions and related statistics with batch and broadcasting semantics. See the Distributions Tutorial.  Bijectors (
tfp.bijectors
): Reversible and composable transformations of random variables. Bijectors provide a rich class of transformed distributions, from classical examples like the lognormal distribution to sophisticated deep learning models such as masked autoregressive flows.
Layer 2: Model Building
 Joint Distributions (e.g.,
tfp.distributions.JointDistributionSequential
): Joint distributions over one or more possiblyinterdependent distributions. For an introduction to modeling with TFP'sJointDistribution
s, check out this colab  Probabilistic Layers (
tfp.layers
): Neural network layers with uncertainty over the functions they represent, extending TensorFlow Layers.
Layer 3: Probabilistic Inference
 Markov chain Monte Carlo (
tfp.mcmc
): Algorithms for approximating integrals via sampling. Includes Hamiltonian Monte Carlo, randomwalk MetropolisHastings, and the ability to build custom transition kernels.  Variational Inference (
tfp.vi
): Algorithms for approximating integrals via optimization.  Optimizers (
tfp.optimizer
): Stochastic optimization methods, extending TensorFlow Optimizers. Includes Stochastic Gradient Langevin Dynamics.  Monte Carlo (
tfp.monte_carlo
): Tools for computing Monte Carlo expectations.
TensorFlow Probability is under active development. Interfaces may change at any time.
Examples
See tensorflow_probability/examples/
for endtoend examples. It includes tutorial notebooks such as:
 Linear Mixed Effects Models. A hierarchical linear model for sharing statistical strength across examples.
 Eight Schools. A hierarchical normal model for exchangeable treatment effects.
 Hierarchical Linear Models. Hierarchical linear models compared among TensorFlow Probability, R, and Stan.
 Bayesian Gaussian Mixture Models. Clustering with a probabilistic generative model.
 Probabilistic Principal Components Analysis. Dimensionality reduction with latent variables.
 Gaussian Copulas. Probability distributions for capturing dependence across random variables.
 TensorFlow Distributions: A Gentle Introduction. Introduction to TensorFlow Distributions.
 Understanding TensorFlow Distributions Shapes. How to distinguish between samples, batches, and events for arbitrarily shaped probabilistic computations.
 TensorFlow Probability Case Study: Covariance Estimation. A user's case study in applying TensorFlow Probability to estimate covariances.
It also includes example scripts such as:
 Variational Autoencoders. Representation learning with a latent code and variational inference.
 VectorQuantized Autoencoder. Discrete representation learning with vector quantization.
 Disentangled Sequential Variational Autoencoder Disentangled representation learning over sequences with variational inference.
 Grammar Variational Autoencoder. Representation learning over productions in a contextfree grammar.
 Latent Dirichlet Allocation (Distributions version, Mixed membership modeling for capturing topics in a document.
 Deep Exponential Family. A deep, sparse generative model for discovering a hierarchy of topics.
 Bayesian Neural Networks. Neural networks with uncertainty over their weights.
 Bayesian Logistic Regression. Bayesian inference for binary classification.
Installation
For additional details on installing TensorFlow, guidance installing prerequisites, and (optionally) setting up virtual environments, see the TensorFlow installation guide.
Stable Builds
To install the latest stable version, run the following:
# Notes: #  The `upgrade` flag ensures you'll get the latest version. #  The `user` flag ensures the packages are installed to your user directory # rather than the system directory. #  TensorFlow 2 packages require a pip >= 19.0 python m pip install upgrade user pip python m pip install upgrade user tensorflow tensorflow_probability
For CPUonly usage (and a smaller install), install with tensorflowcpu
.
To use a pre2.0 version of TensorFlow, run:
python m pip install upgrade user "tensorflow<2" "tensorflow_probability<0.9"
Note: Since TensorFlow is not included
as a dependency of the TensorFlow Probability package (in setup.py
), you must
explicitly install the TensorFlow package (tensorflow
or tensorflowcpu
).
This allows us to maintain one package instead of separate packages for CPU and
GPUenabled TensorFlow. See the
TFP release notes for more
details about dependencies between TensorFlow and TensorFlow Probability.
Nightly Builds
There are also nightly builds of TensorFlow Probability under the pip package
tfpnightly
, which depends on one of tfnightly
or tfnightlycpu
.
Nightly builds include newer features, but may be less stable than the
versioned releases. Both stable and nightly docs are available
here.
python m pip install upgrade user tfnightly tfpnightly
Installing from Source
You can also install from source. This requires the Bazel build system. It is highly recommended that you install
the nightly build of TensorFlow (tfnightly
) before trying to build
TensorFlow Probability from source.
# sudo aptget install bazel git pythonpip # Ubuntu; others, see above links. python m pip install upgrade user tfnightly git clone https://github.com/tensorflow/probability.git cd probability bazel build copt=O3 copt=march=native :pip_pkg PKGDIR=$(mktemp d) ./bazelbin/pip_pkg $PKGDIR python m pip install upgrade user $PKGDIR/*.whl
Community
As part of TensorFlow, we're committed to fostering an open and welcoming environment.
 Stack Overflow: Ask or answer technical questions.
 GitHub: Report bugs or make feature requests.
 TensorFlow Blog: Stay up to date on content from the TensorFlow team and best articles from the community.
 Youtube Channel: Follow TensorFlow shows.
 tfprobability@tensorflow.org: Open mailing list for discussion and questions.
See the TensorFlow Community page for more details. Check out our latest publicity here:
 Coffee with a Googler: Probabilistic Machine Learning in TensorFlow
 Introducing TensorFlow Probability
Contributing
We're eager to collaborate with you! See CONTRIBUTING.md
for a guide on how to contribute. This project adheres to TensorFlow's
code of conduct. By participating, you are expected to
uphold this code.
References
If you use TensorFlow Probability in a paper, please cite:
 TensorFlow Distributions. Joshua V. Dillon, Ian Langmore, Dustin Tran, Eugene Brevdo, Srinivas Vasudevan, Dave Moore, Brian Patton, Alex Alemi, Matt Hoffman, Rif A. Saurous. arXiv preprint arXiv:1711.10604, 2017.
(We're aware there's a lot more to TensorFlow Probability than Distributions, but the Distributions paper lays out our vision and is a fine thing to cite for now.)
Project details
Release history Release notifications  RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Filename, size  File type  Python version  Upload date  Hashes 

Filename, size tensorflow_probability0.11.1py2.py3noneany.whl (4.3 MB)  File type Wheel  Python version py2.py3  Upload date  Hashes View 
Hashes for tensorflow_probability0.11.1py2.py3noneany.whl
Algorithm  Hash digest  

SHA256  e9ce5288ccdb80b6e311d1a2904b5af618a7cd5791d79d6fd051a628087ec0ae 

MD5  3367ef7bc7ec2615632bbf1357c1a775 

BLAKE2256  b39907d4220b021a5d6f6b3de8872f2a634389ad224f8508258452e57aaaf328 