Skip to main content
  • Home
  • Development
  • Documentation
  • Donate
  • Operational login
  • Browse the archive

swh logo
SoftwareHeritage
Software
Heritage
Archive
Features
  • Search

  • Downloads

  • Save code now

  • Add forge now

  • Help

https://github.com/GPflow/GPflow
16 July 2025, 10:58:06 UTC
  • Code
  • Branches (230)
  • Releases (4)
  • Visits
    • Branches
    • Releases
    • HEAD
    • refs/heads/0.5.0
    • refs/heads/alan/hackathon_docs
    • refs/heads/alan/quickfix/multioutput_kernels
    • refs/heads/andrewl/fix_GPR_posterior_leading_dim
    • refs/heads/avullo-willcowley/working-bee-ef1
    • refs/heads/awav/check-det
    • refs/heads/awav/develop-2.0/hmc-helper
    • refs/heads/awav/develop-2.0/update-parameter-docstring
    • refs/heads/awav/different-stuff
    • refs/heads/awav/gpflow-2.0-squared_distances
    • refs/heads/awav/inference
    • refs/heads/awav/kernel-structure
    • refs/heads/awav/likelihood-variance
    • refs/heads/awav/natural-gradients
    • refs/heads/awav/release-pip-package
    • refs/heads/awav/release-testing-branch
    • refs/heads/awav/sparse-tensors-support
    • refs/heads/awav/tensor-functor
    • refs/heads/awav/tfp
    • refs/heads/awav_documentation
    • refs/heads/blockkernel
    • refs/heads/bump_version_to_2_10
    • refs/heads/cone
    • refs/heads/deep
    • refs/heads/deep_arccos_kernel
    • refs/heads/dependabot/pip/black-24.3.0
    • refs/heads/develop
    • refs/heads/develop-1.0
    • refs/heads/eps_conditionals
    • refs/heads/fast-grad
    • refs/heads/felix/pathologies_experiment
    • refs/heads/fergus/anisotropy
    • refs/heads/fergus/het_sgpr
    • refs/heads/fergus/linear
    • refs/heads/fergus/linear_noise
    • refs/heads/fergus/notebook
    • refs/heads/fergus/random_init_lin_noise
    • refs/heads/freeze_as_float32
    • refs/heads/fxsm/new_svgp
    • refs/heads/gh-pages
    • refs/heads/gplvm
    • refs/heads/gplvm-fullcov
    • refs/heads/gustavocmv/heterocedastic-gaussian-likelihood
    • refs/heads/gustavocmv/multiclass-likelihood-quadrature-test
    • refs/heads/gustavocmv/ndiagghquadrature-property-setter
    • refs/heads/gustavocmv/varying-noise-notebook-comment
    • refs/heads/hugh/broadcasting_matched_multi_sample
    • refs/heads/hughsalimbeni-broadcasting-conditional
    • refs/heads/icouckuy-derivatives
    • refs/heads/james-vincent/sgpr
    • refs/heads/jax
    • refs/heads/jesper/1956/stateless_random
    • refs/heads/jesper/dimobjs
    • refs/heads/jesper/dimobjswtf
    • refs/heads/jesper/fix_gpflux
    • refs/heads/jesper/for_hv
    • refs/heads/jesper/jn_gps
    • refs/heads/jesper/warped_halton
    • refs/heads/joelb/type-hint-config
    • refs/heads/john-bradshaw/binary-class-GP
    • refs/heads/john-bradshaw/derivative-observations
    • refs/heads/john-bradshaw/linear-features-for-kernels
    • refs/heads/john-bradshaw/linear-features-for-kernels-gpflow1.0
    • refs/heads/john/linear
    • refs/heads/khurram/scipy_xla
    • refs/heads/mark/jitter
    • refs/heads/master
    • refs/heads/master-1.0
    • refs/heads/master_profile_mnist
    • refs/heads/merging-masters
    • refs/heads/mnist
    • refs/heads/mnist_datatypes
    • refs/heads/multiclass_slicing
    • refs/heads/multioutput
    • refs/heads/nbtest
    • refs/heads/nested_models_recompilation
    • refs/heads/nicolas/sinc_kernel
    • refs/heads/parallel_tests
    • refs/heads/profiling_mods
    • refs/heads/profiling_mods_paper
    • refs/heads/pypi
    • refs/heads/requirements_fix
    • refs/heads/revert-1511-master
    • refs/heads/robustmax_epsilon_learnable
    • refs/heads/sc336/2.7.0-master-merge-again
    • refs/heads/sc336/2.7.0-merge
    • refs/heads/sc336/2.7.1-preparation
    • refs/heads/sc336/3.8_enum_bug
    • refs/heads/sc336/GroupingKey_error
    • refs/heads/sc336/categorical_kernel
    • refs/heads/sc336/dgp_components
    • refs/heads/sc336/fix_conflicts
    • refs/heads/sc336/key_rotation
    • refs/heads/sc336/mypy-sudden-failure
    • refs/heads/sc336/notebook-kernel_link
    • refs/heads/sc336/python-3-11
    • refs/heads/sc336/sphinx_version_switcher
    • refs/heads/sc336/v2.6.4
    • refs/heads/sc336/v2.6.5
    • refs/heads/sc336/version-numbers
    • refs/heads/sergio_pasc/gpflow-2.0/adapt-sgpmc-and-gpmc
    • refs/heads/sergio_pasc/gpflow-2.0/adapt-sgpr
    • refs/heads/sergio_pasc/gpflow-2.0/move-gplvm-tests
    • refs/heads/sergio_pasc/gpflow-2.0/move-multioutput-features-tests
    • refs/heads/sergio_pasc/gpflow-2.0/move-quadrature-tests
    • refs/heads/sergio_pasc/gpflow-2.0/move-tests-methods
    • refs/heads/sergio_pasc/gpflow-2.0/ordinal_regression
    • refs/heads/sergio_pasc/gpflow-2.0/parameter_transform
    • refs/heads/sergio_pasc/gpflow-2.0/remove_training_loop
    • refs/heads/spascual/add-mailmap-file
    • refs/heads/st---metaautoflow
    • refs/heads/st/clean_up_broadcasting_conditionals
    • refs/heads/st/ericpena/natgrad-change
    • refs/heads/st/fix_active_dims_2
    • refs/heads/st/fix_config_module_docstring
    • refs/heads/st/fix_test_method_equivalence
    • refs/heads/st/fix_typo
    • refs/heads/st/fxsm
    • refs/heads/st/fxsm_closure
    • refs/heads/st/inv_probit_jitter_arg
    • refs/heads/st/new_svgp
    • refs/heads/st/posterior
    • refs/heads/st/posterior_with_linear_operators
    • refs/heads/st/quickfix/dispatch_docs
    • refs/heads/st/quickfix/posterior
    • refs/heads/st/quickfix_num_latent
    • refs/heads/st/rename_slow_multioutput
    • refs/heads/st/reorder_covariances
    • refs/heads/st/rescue_754
    • refs/heads/st/snowflake_kernel
    • refs/heads/st/test_cleanup
    • refs/heads/st/test_for_shape_check
    • refs/heads/st/test_kernel
    • refs/heads/st/triangular
    • refs/heads/st_FITCvsVFE_2.0
    • refs/heads/stef/fxsm
    • refs/heads/tf2.0-compatible
    • refs/heads/transform_on_sided
    • refs/heads/uri/bump_version_to_2_9_1
    • refs/heads/uri/bump_version_to_2_9_2
    • refs/heads/uri/clarify_training_loss_ref_in_tutorial
    • refs/heads/uri/dont_use_enums_for_default_values
    • refs/heads/uri/fix_benchmarks
    • refs/heads/uri/heteroskedastic_linear_mean
    • refs/heads/uri/investigate_scipy_memory_leak
    • refs/heads/uri/investigate_tf214_memory_leak
    • refs/heads/uri/move_prod_to_2_14
    • refs/heads/uri/numpy_2
    • refs/heads/uri/pickling_scipy_optimizer
    • refs/heads/uri/prod_test_environment
    • refs/heads/uri/quickfix/dont_round_small_values_in_summary
    • refs/heads/uri/quickfix/mypy_fixes
    • refs/heads/uri/release_2_8_1
    • refs/heads/uri/release_2_9_0
    • refs/heads/uri/support_tf_2_12
    • refs/heads/uri/test
    • refs/heads/uri/test_sgpr_changepoint_issue
    • refs/heads/uri/test_tf_2_16
    • refs/heads/uri/track_loss_history
    • refs/heads/uri/update_max_tf_version
    • refs/heads/uri/update_prod_tf_version
    • refs/heads/v1.5.1-docs
    • refs/heads/va/additive_models
    • refs/heads/va/gpf/conditional_kernel
    • refs/heads/va/gpf/seeger_lik
    • refs/heads/va/h
    • refs/heads/vdutor/multiple-output-gps
    • refs/heads/vincent/add-shared-mixed-mok
    • refs/heads/vincent/cholesky-to-kl
    • refs/heads/vincent/hotfix/preslicing-lmc
    • refs/heads/vincent/hotfix/save-keras-model
    • refs/heads/vincent/introspect-conditional
    • refs/heads/vincent/more-predict-functions
    • refs/heads/vincent/nbviewer
    • refs/heads/vincent/quickfix/dynamic-shapes-quadrature
    • refs/heads/vincent/quickfix/typo
    • refs/heads/vincent/shared-mixed-mok
    • refs/heads/vincent/st/heteroscedastic
    • refs/heads/vincent/st/multi-output-likelihoods
    • refs/heads/vincent/update-readme
    • refs/heads/whitening
    • refs/tags/0.2.1
    • refs/tags/0.3.1
    • refs/tags/0.3.2
    • refs/tags/0.3.3
    • refs/tags/0.3.4
    • refs/tags/0.3.5
    • refs/tags/0.4.0
    • refs/tags/0.5.0
    • refs/tags/1.0.0
    • refs/tags/1.1.0
    • refs/tags/1.1.1
    • refs/tags/2.0.0-rc1
    • refs/tags/v1.4.1
    • refs/tags/v1.5.0
    • refs/tags/v1.5.1
    • refs/tags/v2.0.0
    • refs/tags/v2.0.1
    • refs/tags/v2.0.2
    • refs/tags/v2.0.3
    • refs/tags/v2.0.4
    • refs/tags/v2.0.5
    • refs/tags/v2.1.0
    • refs/tags/v2.1.1
    • refs/tags/v2.1.2
    • refs/tags/v2.1.3
    • refs/tags/v2.1.4
    • refs/tags/v2.1.5
    • refs/tags/v2.10.0
    • refs/tags/v2.2.0
    • refs/tags/v2.2.1
    • refs/tags/v2.3.0
    • refs/tags/v2.3.1
    • refs/tags/v2.4.0
    • refs/tags/v2.5.0
    • refs/tags/v2.5.1
    • refs/tags/v2.5.2
    • refs/tags/v2.6.0
    • refs/tags/v2.6.1
    • refs/tags/v2.6.2
    • refs/tags/v2.6.3
    • refs/tags/v2.6.4
    • refs/tags/v2.6.5
    • refs/tags/v2.7.0
    • refs/tags/v2.7.1
    • refs/tags/v2.8.0
    • refs/tags/v2.8.1
    • refs/tags/v2.9.0
    • refs/tags/v2.9.1
    • refs/tags/v2.9.2
    • v1.3.0
    • v1.2.0
    • pre-dimension-rolling
    • 0.3.9
  • 1ea0c48
  • /
  • README.md
Raw File Download
Take a new snapshot of a software origin

If the archived software origin currently browsed is not synchronized with its upstream version (for instance when new commits have been issued), you can explicitly request Software Heritage to take a new snapshot of it.

Use the form below to proceed. Once a request has been submitted and accepted, it will be processed as soon as possible. You can then check its processing state by visiting this dedicated page.
swh spinner

Processing "take a new snapshot" request ...

Permalinks

To reference or cite the objects present in the Software Heritage archive, permalinks based on SoftWare Hash IDentifiers (SWHIDs) must be used.
Select below a type of object currently browsed in order to display its associated SWHID and permalink.

  • content
  • directory
  • revision
  • snapshot
origin badgecontent badge Iframe embedding
swh:1:cnt:1fa851c683a0e60472c342632a899518b0549d7a
origin badgedirectory badge Iframe embedding
swh:1:dir:1ea0c48c563b0b62943e8235db135f9f2bc8786c
origin badgerevision badge
swh:1:rev:2a755d547574a9cd4bc813ab147cc57a30808737
origin badgesnapshot badge
swh:1:snp:239fa20181c27ca73831654c9488af916c079076
Citations

This interface enables to generate software citations, provided that the root directory of browsed objects contains a citation.cff or codemeta.json file.
Select below a type of object currently browsed in order to generate citations for them.

  • content
  • directory
  • revision
  • snapshot
Generate software citation in BibTex format (requires biblatex-software package)
Generating citation ...
Generate software citation in BibTex format (requires biblatex-software package)
Generating citation ...
Generate software citation in BibTex format (requires biblatex-software package)
Generating citation ...
Generate software citation in BibTex format (requires biblatex-software package)
Generating citation ...
Tip revision: 2a755d547574a9cd4bc813ab147cc57a30808737 authored by Alexander G. de G. Matthews on 04 November 2016, 14:23:00 UTC
Incrementing minor version number to 0.3.4 (#262)
Tip revision: 2a755d5
README.md
# GPflow

GPflow is a package for building Gaussian process models in python, using [TensorFlow](http://www.tensorflow.org). It was originally created and is now managed by [James Hensman](http://www.lancaster.ac.uk/staff/hensmanj/) and [Alexander G. de G. Matthews](http://mlg.eng.cam.ac.uk/?portfolio=alex-matthews). 
The full list of [contributors](http://github.com/GPflow/GPflow/graphs/contributors) (in alphabetical order) is Alexis Boukouvalas, Ivo Couckuyt, Keisuke Fujii, Zoubin Ghahramani, David J. Harris, James Hensman, Pablo Leon-Villagra, Daniel Marthaler, Alexander G. de G. Matthews, Tom Nickson, Valentine Svensson and Mark van der Wilk. GPflow is an open source project so if you feel you have some relevant skills and are interested in contributing then please do contact us.  

[![Python2.7 status](https://codeship.com/projects/26b43920-e96e-0133-3481-02cde9680eda/status?branch=master)](https://codeship.com/projects/147609)
[![Python3.5 Status](https://travis-ci.org/GPflow/GPflow.svg?branch=master)](https://travis-ci.org/GPflow/GPflow)
[![Coverage Status](http://codecov.io/github/GPflow/GPflow/coverage.svg?branch=master)](http://codecov.io/github/GPflow/GPflow?branch=master)
[![Documentation Status](https://readthedocs.org/projects/gpflow/badge/?version=latest)](http://gpflow.readthedocs.io/en/latest/?badge=latest)

# Install

## 1) Install TensorFlow. 
Please see instructions on the main TensorFlow [webpage](https://www.tensorflow.org/versions/r0.10/get_started/os_setup.html#download-and-setup). You will need version 0.11. We find that for most users pip installation is the fastest way to get going.

## 2) install package
GPflow includes some tensorflow extensions that are compiled when you run setup.py.  For those interested in modifying the source of GPflow, we recommend  
```
python setup.py develop
```
but installation should work well too:
```
python setup.py install
```
You can run the tests with `python setup.py test`.

# What's the difference between GPy and GPflow?

GPflow has origins in [GPy](http://github.com/sheffieldml/gpy) by the [GPy contributors](https://github.com/SheffieldML/GPy/graphs/contributors), and much of the interface is intentionally similar for continuity (though some parts of the interface may diverge in future). GPflow has a rather different remit from GPy though:

 -  GPflow leverages TensorFlow for faster/bigger computation
 -  GPflow has much less code than GPy, mostly because all gradient computation is handled by tensorflow.
 -  GPflow focusses on variational inference and MCMC  -- there is no expectation propagation or Laplace approximation.
 -  GPflow does not have any plotting functionality.

# What models are implemented?
GPflow has a slew of kernels that can be combined in a similar way to GPy ([see this tutorial](https://github.com/SheffieldML/notebook/blob/master/GPy/basic_kernels.ipynb)). As for inference, the options are currently:

#### Regression
For GP regression with Gaussian noise, it's possible to marginalize the function values exactly: you'll find this in `GPflow.gpr.GPR`. You can do maximum likelihood or MCMC for the covariance function parameters ([notebook](https://github.com/GPflow/GPflow/blob/master/doc/source/notebooks/regression.ipynb)).

It's also possible to do Sparse GP regression using the `GPflow.sgpr.SGPR` class. This is based on [4].

#### MCMC
For non-Gaussian likelihoods, GPflow has a model that can jointly sample over the function values and the covariance parameters: `GPflow.gpmc.GPMC`. There's also a sparse equivalent in `GPflow.sgpmc.SGPMC`, based on a recent paper [1]. This [notebook](https://github.com/GPflow/GPflow/blob/master/doc/source/notebooks/Sparse%20mcmc%20demo.ipynb) introduces the interface.

#### Variational inference
It's often sufficient to approximate the function values as a Gaussian, for which we follow [2] in `GPflow.vgp.VGP`. In addition, there is a sparse version based on [3] in `GPflow.svgp.SVGP`. In the Gaussian likelihood case some of the optimization may be done analytically as discussed in [4] and implemented in `GPflow.sgpr.SGPR` . All of the sparse methods in GPflow are solidified in [5].

The following table summarizes the model options in GPflow. 

| | Gaussian <br> likelihood | Non-Gaussian <br> (variational) | Non-Gaussian <br> (MCMC)|
| --- | --- | --- | --- |
| Full-covariance | `GPflow.gpr.GPR` | `GPflow.vgp.VGP` | `GPflow.gpmc.GPMC`|
| Sparse approximation | `GPflow.sgpr.SGPR` | `GPflow.svgp.SVGP` | `GPflow.sgpmc.SGPMC` |

### References
[1] MCMC for Variationally Sparse Gaussian Processes
J Hensman, A G de G Matthews, M Filippone, Z Ghahramani
Advances in Neural Information Processing Systems, 1639-1647

[2] The variational Gaussian approximation revisited
M Opper, C Archambeau
Neural computation 21 (3), 786-792

[3] Scalable Variational Gaussian Process Classification
J Hensman, A G de G Matthews, Z Ghahramani
Proceedings of AISTATS 18, 2015

[4] Variational Learning of Inducing Variables in Sparse Gaussian Processes. 
M Titsias
Proceedings of AISTATS 12, 2009

[5] On Sparse variational methods and the Kullback-Leibler divergence between stochastic processes
A G de G Matthews, J Hensman, R E Turner, Z Ghahramani
Proceedings of AISTATS 19, 2016

### Acknowledgements

James Hensman was supported by an MRC fellowship and Alexander G. de G. Matthews was supported by EPSRC grant EP/I036575/1.

back to top

Software Heritage — Copyright (C) 2015–2025, The Software Heritage developers. License: GNU AGPLv3+.
The source code of Software Heritage itself is available on our development forge.
The source code files archived by Software Heritage are available under their own copyright and licenses.
Terms of use: Archive access, API— Contact— JavaScript license information— Web API