0620aa4 | Artem Artemev | 20 October 2018, 09:46:45 UTC | Example. | 20 October 2018, 09:46:45 UTC |
732b0ce | Artem Artemev | 20 October 2018, 07:58:13 UTC | GPflow 2.0 example | 20 October 2018, 07:58:13 UTC |
af76829 | Artem Artemev | 19 October 2018, 09:20:05 UTC | Remove optimizers | 19 October 2018, 09:20:05 UTC |
ebd9fd0 | Artem Artemev | 18 October 2018, 12:46:21 UTC | Add rest of the project | 18 October 2018, 12:46:21 UTC |
ac35aad | Artem Artemev | 18 October 2018, 12:44:03 UTC | Constrained parameter | 18 October 2018, 12:44:03 UTC |
5bbd453 | Artem Artemev | 16 October 2018, 22:22:44 UTC | Cleaning up structure of GPflow 2.0 | 16 October 2018, 22:22:44 UTC |
e826dd2 | Artem Artemev | 16 October 2018, 13:59:35 UTC | Move multioutput | 16 October 2018, 13:59:35 UTC |
99e31e6 | Artem Artemev | 16 October 2018, 13:58:38 UTC | Move multioutput | 16 October 2018, 13:58:38 UTC |
6761391 | Artem Artemev | 09 October 2018, 20:18:15 UTC | Resturcturing gpflow | 09 October 2018, 20:18:15 UTC |
cbc5d2b | Artem Artemev | 09 October 2018, 17:56:37 UTC | Intermediate state of shuffling modules | 09 October 2018, 17:56:37 UTC |
3288c8a | Artem Artemev | 06 October 2018, 18:12:45 UTC | Base file is added | 06 October 2018, 18:12:45 UTC |
6ab346e | Artem Artemev | 06 October 2018, 18:12:10 UTC | Finalise parameters class | 06 October 2018, 18:12:10 UTC |
74f2f06 | Artem Artemev | 20 September 2018, 15:55:39 UTC | Modify kernels | 20 September 2018, 15:55:39 UTC |
f31a914 | Artem Artemev | 20 September 2018, 10:34:08 UTC | Remove unnecessary parts | 20 September 2018, 10:34:08 UTC |
2c4cf39 | Alexander G. de G. Matthews | 17 August 2018, 19:05:27 UTC | Adding widedeepnetworks repository link (#825) * Adding repository link * Correction to table | 17 August 2018, 19:05:27 UTC |
54a276a | st-- | 19 July 2018, 13:19:51 UTC | Parameter.trainable was not properly a property, and param.trainable = False did not work. Fixed by this commit. (#814) | 19 July 2018, 13:19:51 UTC |
f746253 | Vincent Dutordoir | 17 July 2018, 12:58:31 UTC | Fix bug in ndiag_mc re multi-dimensional kwargs (#813) | 17 July 2018, 12:58:31 UTC |
1db48f3 | Artem Artemev | 11 July 2018, 12:50:44 UTC | Update version.py file to 1.2.0 (#812) | 11 July 2018, 12:50:44 UTC |
707b195 | Artem Artemev | 11 July 2018, 11:21:33 UTC | Release notes 1.2.0 (#810) | 11 July 2018, 11:21:33 UTC |
1ff0a87 | Artem Artemev | 11 July 2018, 10:58:39 UTC | Optimizer's step_callback accepts step number (#811) | 11 July 2018, 10:58:39 UTC |
b78c1a8 | ahsimb | 10 July 2018, 11:13:25 UTC | Fixed discovered problem with the monitor, in particular with TensorBoard tasks (#807) | 10 July 2018, 11:13:25 UTC |
495b6eb | Mark van der Wilk | 28 June 2018, 12:59:50 UTC | Softmax fix (#804) * PEP8. * PEP8. * Added `SoftMax.conditional_variance()`. * SoftMax test now tests against `Bernoulli` likelihood, including `predict_mean_and_var`. * super * consistency * test comment * bugfix * fix tests | 28 June 2018, 12:59:50 UTC |
45fed42 | ahsimb | 28 June 2018, 11:57:28 UTC | Big re-work of monitor (#792) * New monitor initial commit * Fixed the monitor notebook (checking that the saving directory exists) * Addressed PR comments. * refactored environment * Attempt to avoid using X server when testing the monitor. * Added few more tests. | 28 June 2018, 11:57:28 UTC |
1851e0d | st-- | 27 June 2018, 11:19:26 UTC | Monte-Carlo likelihoods (#799) * add @markvdw's stochastic likelihood, including the softmax * initial MC likelihood * remove MonteCarloLikelihood base class from tests * fix test * var of predict_mean_and_var and predict_density for MC likelihood * factor out MC sampling * add comment for variance bias * add tests * fixes * use same integration as for GH quadrature in MonteCarloLikelihood.predict_mean_and_var() * . * increase rtol * move to proper use of super() * move MC integration to quadrature module, similar to ndiagquad * seed to make test deterministic * add Assert for shape of Y * tidy up studentT likelihood * fix for heteroskedastic likelihoods -- requires logp to always call the Y argument Y * fix doc * add assert and equivalence tests for SoftMax * remove erroneously added file * rename "probit" to inv_probit (which is what it actually is) * add assert for num_classes to SoftMax * fix whitespace * Update RELEASE.md * Update RELEASE.md | 27 June 2018, 11:19:26 UTC |
1b0f4b0 | ByungJun Lee | 26 June 2018, 10:18:10 UTC | Minibatch shape is unknow by default (#704) | 26 June 2018, 10:18:10 UTC |
9d23839 | st-- | 20 June 2018, 14:59:06 UTC | Notebook to demonstrate advanced usage such as combining GP with Neural Network (#712) * added notebook * added vanilla conv net accuracy * Tidy up notebook * ran notebook * ran notebook #2 * add untested notebooks to test_notebooks * fix bug in natural_gradients notebook * add nb_niter and nb_range to only run a small number of iterations in continuous integration notebook tests * make advanced_usage.ipynb use nb_iter() * don't add natural_gradients.ipynb and upper_bound.ipynb notebook tests in this PR * make advanced_usage run faster in CI * clean up advanced_usage * Update test_notebooks.py * fix notebook_niter * missing input_dim for CI * update notebook * another reset_default_graph_and_session call | 20 June 2018, 14:59:06 UTC |
3a16991 | Hugh Salimbeni | 19 June 2018, 15:00:11 UTC | Removed jitter in nat grads (#768) | 19 June 2018, 15:00:11 UTC |
61088fd | st-- | 19 June 2018, 13:19:35 UTC | Speed up notebooks (#789) Notebooks are slow to execute. Additional utility functions help to detect where notebook are run and control number of iterations (optimization, standard loops and cetera), therefore minimizing spent time on running notebook integration tests. | 19 June 2018, 13:19:35 UTC |
bb08f22 | Vincent Dutordoir | 18 June 2018, 17:04:06 UTC | Multi-output conditionals (#724) * Introduction of MultiOutputFeatures (Mof) and MultiOutputKernels (Mok). These are used to specify a particular setup of multi-output correlation. * Multiple-dispatch for conditional. This allows GPflow to select the most efficient conditional code depending on your choice of Mof and Mok. * Multiple-dispatch for Kuu and Kuf. Previously Kuu(.) and Kuf(.) were member functions of the feature class. This became cumbersome as the calculation of Kuu and Kuf also depends on the kernel used. In line with conditional we now also use multiple-dispatch to calculate Kuu and Kuf for a particular combination of Mok and Mof. * The actual maths to efficiently calculate the output-correlated conditional (credits to @markvdw ) * sample_conditional function that makes sure that the most efficient code is used to get a sample from the conditional distribution. * Minor: we updated a couple of models to use the new multi-output conditional. | 18 June 2018, 17:04:06 UTC |
6baeb43 | jch5f | 15 June 2018, 10:31:27 UTC | Likelihood/students t variance scaling (#777) * Add scaling to studentT conditional variance The conditional variance of the Student’s T distributions is proportional to the square of the scale of the distribution. See https://en.wikipedia.org/wiki/Student%27s_t-distribution#In_terms_of_sca ling_parameter_σ,_or_σ2. I’ve incorporated the correct scaling factor. * explicit scale dtype and tensor broadcasting Added an explicit data type for the Student’s T scale parameter, and made the broadcasting in the conditional_variance method explicit. | 15 June 2018, 10:31:27 UTC |
916458e | st-- | 13 June 2018, 13:21:24 UTC | ndiagquad logspace feature for improved numerical stability (#747) | 13 June 2018, 13:21:24 UTC |
8fa0d57 | Vincent Dutordoir | 13 June 2018, 09:39:00 UTC | Fix failing unittest under TensorFlow 1.8 (#788) | 13 June 2018, 09:39:00 UTC |
0e2ee24 | Joel Wright | 12 June 2018, 19:00:03 UTC | Support Python 3.5.2 in typing checks (Ubuntu 16.04 default python3) (#787) * Support Python 3.5.2 in typing checks (Ubuntu 16.04 default python3) | 12 June 2018, 19:00:03 UTC |
147ce61 | Vincent Dutordoir | 22 May 2018, 21:33:17 UTC | Logger in the settings (#764) | 22 May 2018, 21:33:17 UTC |
d40222d | James Hensman | 17 May 2018, 08:58:16 UTC | Updating readthedocs link in readme to point at master (#760) | 17 May 2018, 08:58:16 UTC |
e5d2d02 | Mark van der Wilk | 16 May 2018, 12:23:23 UTC | Allow `StoreSession` to take `False` for `restore_path` to prevent restoring. (#759) | 16 May 2018, 12:23:23 UTC |
bac9728 | st-- | 10 May 2018, 15:52:22 UTC | fix for Param(shape=(1,)) in ModelTensorBoard (#752) Some parameters of size 1 need to be squeezed to scalars before they can be viewed with TensorBoard. | 10 May 2018, 15:52:22 UTC |
aa98c55 | st-- | 10 May 2018, 14:24:12 UTC | quickfix for bug with params_as_tensors_for (#751) * quickfix for bug with params_as_tensors_for * now last-in first-out as it should be * fix bug in bug fix | 10 May 2018, 14:24:12 UTC |
17781c2 | Mark van der Wilk | 09 May 2018, 18:21:58 UTC | Inclusion of `gpflow-monitor` (#705) * Start integrating gpflow-monitor in actions framework. * Initial commit for GPfow monitor integration with actions framework. * Quick fix to TriggeredAction. * Saver works. * PrintTimings added to actions. * simple callback action added. Needs to handle session correctly * ModelTensorBoard action seems to be working. More testing needed * Exclude monitor from testing. * Check if notebook coverage is included. * Moving back to removing coverage of monitor. * changed callback action to have access to the model * yet another edit to callback action in order to get access to the context * adding type annotations and cleanning up code * changed condition in the triggered action * Notebook, small bugfixes & LmlTensorBoard. * Add very simple test for monitor. * import of tqdm if not installed is now gracefully handled. * Added seq_exp_lin. * `force_run` now first test. * Fix `force_run` bug. * Updated test. * Actions test now also tests `CallbackAction`. | 09 May 2018, 18:21:58 UTC |
f867d66 | st-- | 08 May 2018, 19:57:48 UTC | Improve docstring of Periodic kernel (#745) | 08 May 2018, 19:57:48 UTC |
20a006f | st-- | 05 May 2018, 22:52:53 UTC | Copyright notes | 05 May 2018, 22:52:53 UTC |
b9e5817 | st-- | 04 May 2018, 15:50:12 UTC | Improved quadrature for likelihoods (#736) * introduce ndiagquad to unify quadrature in likelihoods * ndiagquad that can cope with several dimensions over which to integrate * add pragma: no cover to error checking * small change of signature * fix for multi-parameter likelihoods * preliminary quadrature test * improved quadrature test * fix weight normalisation in ndiagquad * improve test * add some type annotations * more quadrature tests | 04 May 2018, 15:50:12 UTC |
38b2e90 | Adrià Garriga | 03 May 2018, 21:35:06 UTC | Gauss kl method is unable to work with unknown shape of the guassian parameters | 03 May 2018, 21:35:06 UTC |
69dbeb1 | st-- | 02 May 2018, 20:30:06 UTC | Extend contributing.md | 02 May 2018, 20:30:06 UTC |
da10b35 | st-- | 02 May 2018, 11:15:56 UTC | Copy values of parameters in as_pandas_table method to make them independent from ongoing changes during optimization. | 02 May 2018, 11:15:56 UTC |
ee4f774 | Artem Artemev | 02 May 2018, 09:00:50 UTC | GPflow scipy optimizer doesn't pass options kwargs to actual scipy optimizer correctly. (#738) | 02 May 2018, 09:00:50 UTC |
3b49709 | st-- | 01 May 2018, 09:09:36 UTC | Unify calling signature of (log)densities (#721) * rename densities -> logdensities * unify ordering of (log)densites to have random variable first * adjust logdensities test * forgot to git add * fix Exponential prior * fix Exponential prior #2 * minor change of notation * move to format strings * Uniform.log_height as property * logdensities: rename y -> x | 01 May 2018, 09:09:36 UTC |
ae7ed2c | Nikitas Rontsis | 30 April 2018, 20:59:29 UTC | Numerically stable scaled squred distance via clipping near to 0. | 30 April 2018, 20:59:29 UTC |
aae4f34 | John | 30 April 2018, 17:50:31 UTC | Allow the epsilon parameter of the Robustmax likelihood to be trainable (#635) * Robustmax epsilon learnable * Robustmax epsilon a parameter * eps_K1 now a property so that changes with epsilon * test for this property being up to date * updated multiclass notebook to show how it could work * . * cosmetic change * update notebook following merge conflict | 30 April 2018, 17:50:31 UTC |
4a13271 | st-- | 30 April 2018, 16:35:23 UTC | Add Exponential distribution as prior (#717) * Support exponential distribution as prior. The exponential distribution here is parametrized using the rate parameter lambda and always has its mode at 0. * Reuse exponential density for prior distribution Add transformation to test of exponential prior This ensures that it is only evaluated on the positive domain * Add sample method * fix test * fix test again * more fixes * add pragma: no cover to make codecov happy * add sample tests * sample test * revert change to densities.exponential() * fix * pr comments * fix test * removing commented code | 30 April 2018, 16:35:23 UTC |
e59ff2f | st-- | 30 April 2018, 10:44:40 UTC | add shape check for ARD hyperparameters to Kernel classes (#694) * add check of lengthscales shape to Stationary kernel * refactor to _validate_ard_shape * add casts to float * fix ArcCosine test * add None to ARD test * remove deprecated num_gauss_hermite_points from kernel * Clean up docstrings & make code a bit shorter. * Typo ARG => ARD. * update docstring * more dtype=float_type | 30 April 2018, 10:44:40 UTC |
3ff6110 | John Pearson | 27 April 2018, 13:36:43 UTC | returning var_list to Optimizer in order - Issue appears to affect only ScipyOptimizer. Does not affect, e.g., AdamOptimizer on doc/source/notebook/classification - Appears to be due to the fact that TensorFlow variables are not stably ordered across across replications, so var_list (and thus random initial values for optimization) is not either. | 27 April 2018, 13:36:43 UTC |
913bfe3 | James Hensman | 27 April 2018, 08:12:54 UTC | Minor clean-up * removing old notebooks dir * add symbolic link to notebooks | 27 April 2018, 08:12:54 UTC |
f31223c | James Hensman | 26 April 2018, 13:53:52 UTC | Merge pull request #731 from GPflow/jameshensman-tidy1 removing errant file | 26 April 2018, 13:53:52 UTC |
c7acc2f | James Hensman | 26 April 2018, 13:28:03 UTC | removing errant file | 26 April 2018, 13:28:03 UTC |
5e841b7 | Artem Artemev | 19 April 2018, 14:24:02 UTC | Model saver (#660) GPflow model saver. Supports native GPflow models and provides an interface for defining custom savers for user's models. Saver stores GPflow structures and pythonic types as numpy structured arrays and serializes them using HDF5. | 19 April 2018, 14:24:02 UTC |
2fb4b6d | Artem Artemev | 17 April 2018, 14:24:05 UTC | Merge pull request #723 from GPflow/awav/fix-pytest-import Pytest used by test_util module | 17 April 2018, 14:24:05 UTC |
26254a2 | Artem Artemev | 17 April 2018, 13:54:02 UTC | Bump patch version to 1.1.1 | 17 April 2018, 13:54:02 UTC |
753aa2e | Artem Artemev | 17 April 2018, 13:53:21 UTC | pytest must be included as a dependency | 17 April 2018, 13:53:21 UTC |
8a412f6 | Artem Artemev | 12 April 2018, 10:05:11 UTC | Merge pull request #713 from GPflow/awav/github-templates GitHub PR and issue templates. | 12 April 2018, 10:05:11 UTC |
46c8784 | Artem Artemev | 12 April 2018, 09:24:05 UTC | Python code block as an example. | 12 April 2018, 09:24:05 UTC |
e3aba01 | Artem Artemev | 12 April 2018, 09:22:12 UTC | Merge branch 'awav/github-templates' of github.com:GPflow/GPflow into awav/github-templates | 12 April 2018, 09:22:12 UTC |
ec43181 | Artem Artemev | 12 April 2018, 09:22:02 UTC | Content table had broken links | 12 April 2018, 09:22:02 UTC |
ee5c897 | Artem Artemev | 12 April 2018, 09:08:21 UTC | Merge branch 'master' into awav/github-templates | 12 April 2018, 09:08:21 UTC |
eb6a269 | Artem Artemev | 12 April 2018, 09:08:00 UTC | Merge pull request #714 from GPflow/awav/optimizers-fix Optimizers incompatibility with TensorFlow >= 1.6 | 12 April 2018, 09:08:00 UTC |
c5f8520 | st-- | 11 April 2018, 23:13:12 UTC | Update ISSUE_TEMPLATE.md | 11 April 2018, 23:13:12 UTC |
9ccf2b4 | st-- | 11 April 2018, 23:11:35 UTC | Update ISSUE_TEMPLATE.md | 11 April 2018, 23:11:35 UTC |
d15a401 | Artem Artemev | 11 April 2018, 22:14:37 UTC | Change tensorflow version on 1.6 | 11 April 2018, 22:14:37 UTC |
745dcf8 | Artem Artemev | 11 April 2018, 22:01:29 UTC | Bump tensorflow version requirement to 1.5 | 11 April 2018, 22:01:29 UTC |
5e57df5 | Artem Artemev | 11 April 2018, 21:34:46 UTC | TensorFlow optimize initilizer. | 11 April 2018, 21:34:46 UTC |
d05309e | Artem Artemev | 11 April 2018, 20:00:19 UTC | Fixes after code review. | 11 April 2018, 20:20:35 UTC |
ebc8d56 | Artem Artemev | 11 April 2018, 16:01:55 UTC | Merge branch 'awav/github-templates' of github.com:GPflow/GPflow into awav/github-templates | 11 April 2018, 16:01:55 UTC |
96e918d | st-- | 11 April 2018, 16:00:43 UTC | Update contributing.md | 11 April 2018, 16:00:43 UTC |
a6f48fa | Artem Artemev | 11 April 2018, 15:31:36 UTC | Fix typo. | 11 April 2018, 15:31:36 UTC |
1c5c7fb | st-- | 11 April 2018, 15:27:13 UTC | Update README.md Small changes inline | 11 April 2018, 15:27:13 UTC |
6d58de8 | st-- | 11 April 2018, 15:23:32 UTC | Update PULL_REQUEST_TEMPLATE.md Small changes inline | 11 April 2018, 15:23:32 UTC |
28e043c | Artem Artemev | 11 April 2018, 15:10:17 UTC | Brushing up parts of PR template. | 11 April 2018, 15:10:17 UTC |
6d5e10d | Artem Artemev | 11 April 2018, 14:34:36 UTC | Compatibility section in README.md | 11 April 2018, 14:34:36 UTC |
ea4f07d | Artem Artemev | 11 April 2018, 14:19:34 UTC | Modify contributing.md file and add github templates. | 11 April 2018, 14:19:34 UTC |
f5d8cc4 | Guido Kraemer | 04 April 2018, 11:10:45 UTC | Name attribute for Gaussian likelihood. | 04 April 2018, 11:10:45 UTC |
70f18c1 | st-- | 04 April 2018, 10:13:53 UTC | allow params_as_tensors_for() to take several objects as varargs (#672) Allow params_as_tensors_for() to take several objects as varargs | 04 April 2018, 10:13:53 UTC |
455a71f | Artem Artemev | 04 April 2018, 08:27:29 UTC | Merge pull request #701 from ialong/expectations expectations: pass num hermite points to _expectation() and minor cleaning | 04 April 2018, 08:27:29 UTC |
731c5dc | Artem Artemev | 04 April 2018, 08:02:40 UTC | Merge branch 'master' into expectations | 04 April 2018, 08:02:40 UTC |
919ea6f | Artem Artemev | 03 April 2018, 22:32:39 UTC | Docstring updates. | 03 April 2018, 22:32:39 UTC |
29fe092 | Adrià Garriga | 03 April 2018, 22:18:10 UTC | Fixed regression to bug in #615 (#700) * Fixed regression to bug in #615 Refactoring `expectations.py` re-introduced the bug fixed by #615, for which we decided to not introduce a test. This contains the bug fix and the test. * Removed magic number, rewrote test to convention, removed unused import Basically incorporated all of @awav's suggestions + removed an unused import. | 03 April 2018, 22:18:10 UTC |
f076951 | Alessandro Davide Ialongo | 28 March 2018, 16:45:06 UTC | expectations: pass num hermite points to _expectation() and minor cleaning | 03 April 2018, 17:06:16 UTC |
16570be | Artem Artemev | 29 March 2018, 10:51:23 UTC | NatGrads notebook cleanup (#696) * added notebook * added callback to first example * Clean up Natural Gradients notebook. * Final change in NatGrads notebook. * Address PR review. Typo in conjugate case. Likelihood printing. * Conjugate to non-conjugate. | 29 March 2018, 10:51:23 UTC |
e2acd61 | Hugh Salimbeni | 28 March 2018, 11:10:42 UTC | Natural gradients notebook (#691) * added notebook * added callback to first example | 28 March 2018, 11:10:42 UTC |
c283fec | Artem Artemev | 27 March 2018, 10:27:17 UTC | GPflow Actions. (#678) * Action initials. * Introducing actions. * Change implicit interfaces for an optimizer. * Add simple action tests. * Natural gradient integration. * Unify natural gradient optimizer interface. * Fix NatGradOptimizer test. * Forgot to add actions.py file. | 27 March 2018, 10:27:17 UTC |
f3fe7da | ADAM | 26 March 2018, 13:21:04 UTC | Update gauss_kl to work with K matrices of shape L x M x M (previously M x M only) (#682) Update gauss_kl to work with K matrices of shape L x M x M | 26 March 2018, 13:21:04 UTC |
25116dc | Artem Artemev | 26 March 2018, 09:20:50 UTC | Merge pull request #688 from a5a/master Fixed ModuleNotFoundError | 26 March 2018, 09:20:50 UTC |
5fbff19 | asa | 22 March 2018, 17:17:56 UTC | fixed ModuleNotFoundError in natgrad_optimizer | 22 March 2018, 17:17:56 UTC |
ef45c39 | Artem Artemev | 20 March 2018, 12:37:23 UTC | Merge pull request #674 from GPflow/awav/natural-gradient-optimizer Natural Gradient Optimizer | 20 March 2018, 12:37:23 UTC |
aa3821b | Hugh Salimbeni | 16 March 2018, 14:59:38 UTC | Update doc strings for XiTransformation and add explanation to NatGrad tests. | 20 March 2018, 10:16:55 UTC |
9d8f3c1 | Artem Artemev | 15 March 2018, 23:19:55 UTC | Merge with updated branch. | 15 March 2018, 23:27:18 UTC |
0342cb9 | Artem Artemev | 15 March 2018, 23:18:25 UTC | SVGP vs SGPR optimization test fixed. | 15 March 2018, 23:18:25 UTC |
80528a3 | hrs13 | 14 March 2018, 13:25:41 UTC | added tests for xi transforms, and added nasty placeholder_with_default | 14 March 2018, 13:25:41 UTC |
6014011 | James Hensman | 14 March 2018, 11:48:31 UTC | Merge branch 'master' into awav/natural-gradient-optimizer | 14 March 2018, 11:48:31 UTC |
0bb77c3 | Artem Artemev | 11 March 2018, 23:15:40 UTC | Merge pull request #652 from GPflow/james/py27_docfix Py27 doc fix. | 11 March 2018, 23:15:40 UTC |
9c84c43 | Artem Artemev | 11 March 2018, 22:02:25 UTC | Merge branch 'master' into james/py27_docfix | 11 March 2018, 22:02:25 UTC |