e7879b0 | st-- | 13 March 2020, 21:28:34 UTC | Reactivate notebook tests (#1317) * fix notebooks tests * add test to ensure notebook tests cannot silently fail anymore * fix num_latent -> num_latent_gps in notebooks * clarify comment in notebook | 13 March 2020, 21:28:34 UTC |
87ef583 | st-- | 13 March 2020, 19:20:30 UTC | Update convolutional.pct.py (#1314) patch_size -> patch_shape, IMG_SIZE -> IMAGE_SHAPE | 13 March 2020, 19:20:30 UTC |
dbafb10 | st-- | 13 March 2020, 19:15:14 UTC | Make conditionals function signatures consistent (#1315) * function -> f | 13 March 2020, 19:15:14 UTC |
3f6ac63 | Eric Hammy | 13 March 2020, 17:44:58 UTC | rename num_latent to num_latent_gps (#1310) | 13 March 2020, 17:44:58 UTC |
6fbc356 | st-- | 13 March 2020, 17:28:18 UTC | Rename base kernel in Periodic and Convolutional Kernel to base_kernel (#1312) * Periodic kernel: base -> base_kernel * Convolutional: basekern -> base_kernel * img_size -> image_shape, patch_size -> patch_shape | 13 March 2020, 17:28:18 UTC |
6575e90 | st-- | 13 March 2020, 17:24:58 UTC | Update Makefile: add 'make format' (#1313) and clean up Makefile | 13 March 2020, 17:24:58 UTC |
46809a1 | Artem Artemev | 12 March 2020, 21:56:14 UTC | Adds the freeze method for converting tf.Variable to Tensor constants in tf.Module (#1293) | 12 March 2020, 21:56:14 UTC |
fc40393 | Vincent Dutordoir | 12 March 2020, 16:02:29 UTC | Broadcasting of kernels reintroduced (#1308) Broadcasting kernels: rescue PR #895 | 12 March 2020, 16:02:29 UTC |
6f55e04 | st-- | 12 March 2020, 15:51:43 UTC | fix more images in the gpflow2 upgrade guide (#1305) Remove all underscores from inside ![...] | 12 March 2020, 15:51:43 UTC |
833291f | st-- | 12 March 2020, 12:09:59 UTC | Update intro.rst (#1307) | 12 March 2020, 12:09:59 UTC |
a00cc3b | st-- | 12 March 2020, 12:09:42 UTC | Minor performance improvement: pass Cholesky of K to gauss_kl (#1306) Adds option to pass `K_cholesky` to kullback_leiblers.gauss_kl() for the unwhitened case, instead of `K`. It prevents the double cost of inverting `K` twice, in both conditionals and gauss_kl. | 12 March 2020, 12:09:42 UTC |
dd6c59b | Vincent Dutordoir | 11 March 2020, 14:29:32 UTC | Quickfix: speedup convolutional notebook (#1304) Reduce image size in convolutional notebook. Fixes #1300 | 11 March 2020, 14:29:32 UTC |
07aa9d2 | st-- | 11 March 2020, 00:02:10 UTC | fix gpflow2_upgrade_guide notebook heading levels and images (#1299) | 11 March 2020, 00:02:10 UTC |
7fd3068 | Artem Artemev | 10 March 2020, 10:33:43 UTC | Introduce black formatter (#1294) | 10 March 2020, 10:33:43 UTC |
ebf2c8b | joelberkeley-pio | 03 March 2020, 21:53:23 UTC | use natgrad optimizer in varying noise notebook (#1270) Put natgrads back into the varying noise notebook. Resolves #1173 | 03 March 2020, 21:53:23 UTC |
5f79844 | st-- | 26 February 2020, 14:58:51 UTC | clean up SGPR common __init__ (#1289) `gpflow.models.sgpr` contains two sparse GP models, SGPR and GPRFITC. They had a common subclass to provide the upper_bound() method. They also have the same `__init__`, which is unified in this PR. | 26 February 2020, 14:58:51 UTC |
398c49b | st-- | 26 February 2020, 14:58:21 UTC | Black on tests (#1290) | 26 February 2020, 14:58:21 UTC |
57d8ab7 | st-- | 26 February 2020, 14:09:18 UTC | improve organization of test modules (#1288) Historically, there was just a single flat directory full of test modules. This had several negative implications: a) some test files ended up very long, b) it was occasionally hard to find a good place for new tests, c) no separation between unit and integration tests. This PR gives the tests a directory structure that mirrors that of the gpflow package. Where possible, the code in gpflow/submodule/file.py is tested in tests/gpflow/submodule/test_file.py. Integration tests (e.g. notebooks, method equivalence) are now in tests/integration/. Most of this PR is simple file moves, plus some splitting up of tests (particularly for models) according to the new structure. The reference kernel implementations are now unified in tests/gpflow/kernels/reference.py. | 26 February 2020, 14:09:18 UTC |
f8ee093 | Vincent Dutordoir | 26 February 2020, 09:52:47 UTC | Remove the use of generator in dispatcher (#1264) GPflow makes use of a multipledispatch Dispatcher that internally uses a generator. However, according to TensorFlow [Capabilities and Limitations](https://github.com/tensorflow/tensorflow/blob/560e2575ecad30bedff5b192f33f6d06b19ccaeb/tensorflow/python/autograph/LIMITATIONS.md) generators are not supported by AutoGraph and probably will never be. Thus, compiling code that passed though the dispatcher led to the following warnings: ```bash WARNING:tensorflow:Entity <bound method Dispatcher.dispatch_iter of <dispatched sample_conditional>> appears to be a generator function. It will not be converted by AutoGraph. WARNING: Entity <bound method Dispatcher.dispatch_iter of <dispatched sample_conditional>> appears to be a generator function. It will not be converted by AutoGraph. WARNING:tensorflow:Entity <bound method Dispatcher.dispatch_iter of <dispatched conditional>> appears to be a generator function. It will not be converted by AutoGraph. WARNING: Entity <bound method Dispatcher.dispatch_iter of <dispatched conditional>> appears to be a generator function. It will not be converted by AutoGraph. ``` This PR still uses the same dispatcher, but overwrites the problematic method that uses python generators and replaces it by a simple list. ### NOTE As of this PR we do not need to write `autograph=False` in `tf.function` anymore, and all the code inside dispatching gets compiled the same way as everything else :) ! | 26 February 2020, 09:52:47 UTC |
002b217 | st-- | 25 February 2020, 23:00:29 UTC | Make notebooks deterministic (#1265) Adds random seed setting as required to the various notebooks under doc/source/notebooks to make sure they're as reproducible as possible (i.e., re-running shouldn't change the git diff). There are still some issues with tailor/gp_nn (tensor shape warnings, and bad accuracy) tailor/mixture_density_networks (autograph warnings despite setting autograph=False?) | 25 February 2020, 23:00:29 UTC |
1bd337f | st-- | 25 February 2020, 17:39:30 UTC | minor docstring/code cleanup (#1277) | 25 February 2020, 17:39:30 UTC |
3e8bf18 | Vincent Dutordoir | 25 February 2020, 17:39:09 UTC | Auto-generate docs in GPflow/docs (#1275) This PR (superseding #1271) enables auto-generation of all of GPflow's documentation. Upon a new merge in `develop`, we trigger our new repo [GPflow/docs](https://github.com/GPflow/docs) to: - copy the complete content of GPflow/doc - compile the notebooks `.ipynb` from the `.pct.py` files - create the `rst` files for the api documentation required for readthedocs. #### TODO: - [ ] Allow for documentation at different tags of the source code. | 25 February 2020, 17:39:09 UTC |
167973b | joelberkeley-pio | 25 February 2020, 16:13:08 UTC | Preserve types in deepcopy (#1285) | 25 February 2020, 16:13:08 UTC |
7c851ec | Nils | 23 February 2020, 18:14:35 UTC | add `kerndisc` to projects section (#1273) | 23 February 2020, 18:14:35 UTC |
3317868 | st-- | 21 February 2020, 16:07:26 UTC | Docs quickfixes (#1272) | 21 February 2020, 16:07:26 UTC |
c0aab32 | Artem Artemev | 20 February 2020, 13:23:46 UTC | Add `make` to Docker image (#1269) | 20 February 2020, 13:23:46 UTC |
b035b21 | Artem Artemev | 20 February 2020, 11:25:43 UTC | Config accepts environment variables (#1262) | 20 February 2020, 11:25:43 UTC |
72531a7 | Artem Artemev | 19 February 2020, 17:17:02 UTC | Remove masking kwargs (#1261) | 19 February 2020, 17:17:02 UTC |
96d686f | st-- | 14 February 2020, 15:56:24 UTC | Add documentation of parameter copying to notebooks (#1259) * fix _repr_html_ * update intro_to_gpflow2 notebook with example use of gpflow.utilities.{parameter_dict, multiple_assign} * update upper_bound notebook to remove workaround for #1119 (and add another one for #1260) | 14 February 2020, 15:56:24 UTC |
2c318e8 | Eric Hammy | 14 February 2020, 15:10:29 UTC | Shared interface for number of latent gps in multi-output kernels (#1167) * Add an abstract property to the multioutput GPs returning the number of latents * Should be useful in validation in down the line assembly of multioutput GPs | 14 February 2020, 15:10:29 UTC |
22e14d7 | st-- | 14 February 2020, 14:53:54 UTC | fix link function bug in binary classification notebook (#1243) * fix link function bug in binary classification notebook | 14 February 2020, 14:53:54 UTC |
22edd92 | st-- | 14 February 2020, 14:49:30 UTC | Improve documentation and behaviour of Coregion kernel (#1255) - clean up of the documentation - changes initialization from W=zeros() to W=0.1*ones() which makes it easier to use out of the box - no longer requires manual assigning of symmetry-breaking values to the W matrix after kernel construction - adds output_covariance() method that computes the covariance between outputs (and output_variance() for its diagonal) | 14 February 2020, 14:49:30 UTC |
fea9f0c | Neil Ferguson | 14 February 2020, 11:40:21 UTC | Fix type declaration for LossClosure (#1257) Co-authored-by: Neil Ferguson <44374733+pio-neil@users.noreply.github.com> | 14 February 2020, 11:40:21 UTC |
077e066 | Neil Ferguson | 13 February 2020, 22:08:09 UTC | Added docs for method parameter (#1256) | 13 February 2020, 22:08:09 UTC |
3f5cdd8 | st-- | 13 February 2020, 11:37:15 UTC | Improve documentation and behaviour of Periodic kernel (#1231) Previously, `Periodic` did not take active_dims, but the Kernel base class specifies active_dims as part of the interface, so this PR adds getter/setter that pass through to the base kernel, as well as accepting active_dims in the Periodic() constructor but raising an error when it is not consistent with base.active_dims. | 13 February 2020, 11:37:15 UTC |
24426b3 | joelberkeley-pio | 13 February 2020, 11:30:15 UTC | include special methods in docs (#1253) Closes #1039. With this change, all special methods and functions such as __init__ will be included in the Sphinx docs. | 13 February 2020, 11:30:15 UTC |
1164235 | Eric Hammy | 11 February 2020, 14:27:49 UTC | Inconisistency on whether q_sqrt is triangular fixed. (#1223) * Inconisistency on whether q_sqrt is triangular fixed. Problem: * KL divergence calculations only take lower triangle parts of q_sqrt in their calculation (implying a lower triangular parameterisation of covariance) * Conditional calculations perform calculations using the whole of q_sqrt. * The end result is if you forgot to add the triangular transform to the q_sqrt, your forward pass may be the same (if you initialise with a triangular matrix), but your gradients will immediately stop q_sqrt being triangular. Fix: * Conditional calulcations now only take the lower triangle parts of q_sqrt in their calculation | 11 February 2020, 14:27:49 UTC |
7275533 | elvijs | 10 February 2020, 08:50:03 UTC | Ship type information as specified by PEP 561 (#1251) This way, any consumers using MyPy will be able to get type hints from GPflow | 10 February 2020, 08:50:02 UTC |
f30d42c | Fergus | 09 February 2020, 16:37:22 UTC | Priors on constrained and unconstrained parts of a parameter (#1177) | 09 February 2020, 16:37:22 UTC |
056e59f | st-- | 06 February 2020, 17:06:04 UTC | fix Parameter.__repr__ behaviour within tf.function/graph mode (#1247) Parameter.__repr__ called .numpy() on the constrained and unconstrained representations - this throws an error when in graph mode (tf.function-wrapped), which can lead to errors-in-exception-handling, so this PR makes use of tf.eagerly_executing() to check whether we are in graph mode, and if so, only print shapes and dtype, not values. | 06 February 2020, 17:06:04 UTC |
8dbf7ad | st-- | 03 February 2020, 14:58:01 UTC | remove presliced from Brownian kernel in kernel_design notebook (#1242) #1235 removed the presliced argument from a Kernel's K and K_diag methods, but hadn't amended the custom Brownian kernel in the kernel_design notebook: fixed by this PR. | 03 February 2020, 14:58:01 UTC |
27b0770 | st-- | 03 February 2020, 14:00:53 UTC | jupytext for notebooks (#1239) Makes use of Jupytext to store notebook source in a more readable format, which should make PR reviewing as well as fixing bugs much more straightforward. Also provides a Makefile to regenerate .ipynb from source. * `make pair-ipynb` was used to create the .pct.py/.md versions off the .ipynb in `develop`. * `make all` will execute all .pct.py/.md jupytext notebooks to recreate the .ipynb (this may change the figures in notebooks that haven't had numpy/tensorflow random seeds set yet) * test_notebooks now runs .pct.py/.md in the CI | 03 February 2020, 14:00:53 UTC |
40b2727 | Artem Artemev | 03 February 2020, 10:18:54 UTC | Clear chain of bijectors (#1238) | 03 February 2020, 10:18:54 UTC |
bd1e9c0 | st-- | 31 January 2020, 15:59:08 UTC | Clean up `presliced` argument to kernel calls (#1235) In GPflow 1, each kernel's K and K_diag method was supposed to take a presliced argument. Not all kernels actually had this signature, and not all kernels who had this signature actually did anything with the argument. This PR makes presliced an argument solely to the kernel's __call__, with the intent of making the entire set-up a lot cleaner. | 31 January 2020, 15:59:08 UTC |
cf89f9d | st-- | 29 January 2020, 22:14:24 UTC | Improve explanation of RobustMax likelihood (#1228) * save answer to #1202 in documentation | 29 January 2020, 22:14:24 UTC |
7b550b7 | st-- | 29 January 2020, 12:19:45 UTC | Make it clearer to users that we would welcome feedback on pain points & design quirks as well as "obvious" bugs (#1227) | 29 January 2020, 12:19:45 UTC |
f49e110 | st-- | 28 January 2020, 12:40:15 UTC | Improve pretty-printing of GPflow objects in IPython shell and jupyter notebook (#1233) Makes all GPflow objects (kernels, likelihoods, ...) inherit from gpflow.base.Module (not tf.Module), and adds _repr_html_ and _repr_pretty_ methods to gpflow.base.Module that return appropriate rich representation for jupyter notebook and IPython shell, respectively. * use gpflow.base.Module instead of tf.Module inside gpflow * add _repr_html_ and _repr_pretty_ to gpflow.base.Module for improved display in IPython shell/jupyter notebook * update explicit imports in gpflow/__init__.py | 28 January 2020, 12:40:15 UTC |
8a73e6d | st-- | 22 January 2020, 11:35:49 UTC | Update README.md: GPflow slack invite, stackoverflow vs github issues, installation instructions (#1225) * Restructure "GPflow Community" section in README.md * Update README.md installation instructions | 22 January 2020, 11:35:49 UTC |
e2572c5 | Artem Artemev | 22 January 2020, 00:52:06 UTC | Remove TFP deprecated bijector (#1220) | 22 January 2020, 00:52:06 UTC |
7a943fd | Artem Artemev | 21 January 2020, 16:25:44 UTC | Bump TF and TFP version (#1221) | 21 January 2020, 16:25:44 UTC |
2decaaf | st-- | 21 January 2020, 15:27:17 UTC | Minor fixes (#1222) | 21 January 2020, 15:27:17 UTC |
03a4e29 | st-- | 16 January 2020, 12:24:14 UTC | Fix issue with tf.cast() and implicit dtype conversion (#1211) | 16 January 2020, 12:24:14 UTC |
36a0853 | st-- | 15 January 2020, 11:10:26 UTC | Link GPflow 2 upgrade guide from intro.ipynb and README.md (#1210) | 15 January 2020, 11:10:26 UTC |
fcd3b00 | st-- | 15 January 2020, 11:08:14 UTC | Add validation to Parameter.assign() to increase robustness of transforms (#1198) | 15 January 2020, 11:08:14 UTC |
cd55917 | st-- | 15 January 2020, 11:01:56 UTC | Skip tests more selectively (#1194) | 15 January 2020, 11:01:56 UTC |
4a3bd56 | Neil Ferguson | 14 January 2020, 14:42:43 UTC | Add GPflow 2 upgrade guide (#1199) | 14 January 2020, 14:42:43 UTC |
b17df8b | st-- | 10 January 2020, 16:48:50 UTC | reinstate project links in README.md that disappeared when changing develop to 2.0 | 10 January 2020, 16:48:50 UTC |
7c2711f | st-- | 10 January 2020, 15:55:34 UTC | TensorFlow 2.1 compatibility, and identify as gpflow.Parameter in repr() to ease debugging (#1201) * Adds is_tensor_like property (returns True) to gpflow.Parameter to be compatible with TensorFlow 2.1. * Changes gpflow.Parameter.__repr__ to identify itself as a gpflow object, not a tf.Tensor, to ease debugging and interactive use. | 10 January 2020, 15:55:34 UTC |
6a455db | st-- | 07 January 2020, 21:15:01 UTC | dynamic shape evaluation instead of static shapes (#1181) Allows gpflow2 to work better with tf.function() when static shapes are unknown (e.g. when minibatching). Closes #1179 Co-authored-by: marcoadurno <marco.adurno@gmail.com> | 07 January 2020, 21:15:01 UTC |
fb66fb5 | Artem Artemev | 07 January 2020, 21:12:15 UTC | Improve Parameter.assign docstring (#1193) Closes #1191 | 07 January 2020, 21:12:15 UTC |
ec54849 | Vincent Adam | 07 January 2020, 21:09:47 UTC | Update intro_to_gpflow2.ipynb (#1196) fix minor typo | 07 January 2020, 21:09:47 UTC |
b0e09ee | tadejkrivec | 18 December 2019, 16:33:10 UTC | Update SGPR_notes.ipynb (#1186) | 18 December 2019, 16:33:10 UTC |
426f6d2 | st-- | 17 December 2019, 13:28:10 UTC | Add jit flag to gpflow.optimizers.Scipy (#1190) * Add jit flag to gpflow.optimizers.Scipy that wraps objective and gradient evaluation in tf.function() | 17 December 2019, 13:28:10 UTC |
552074a | st-- | 09 December 2019, 14:24:19 UTC | fix bug in Kernel.on_separate_dims (#1178) * fix bug in Kernel.on_separate_dims * regression test | 09 December 2019, 14:24:19 UTC |
ef5a7ca | Artem Artemev | 04 December 2019, 15:00:19 UTC | Don't mention dockerfile in docs (#1174) Closes #620 | 04 December 2019, 15:00:19 UTC |
8939a38 | st-- | 04 December 2019, 14:51:22 UTC | Clean up kernel interface (#1170) * make kernel interface consistent (uses X, X2 everywhere now) * add ABC metaclass to Kernel baseclass | 04 December 2019, 14:51:22 UTC |
beebbca | st-- | 04 December 2019, 12:27:58 UTC | add links to v1.5 documentation to README.md (#1171) | 04 December 2019, 12:27:58 UTC |
438a3ed | st-- | 03 December 2019, 16:15:40 UTC | add prior to print_summary (#1168) * refactor tabulate_module_summary * add representation of prior to tabulate_module_summary (fixes #1117) | 03 December 2019, 16:15:40 UTC |
b1a6e69 | akhayes | 29 November 2019, 11:41:51 UTC | GPflow notebooks - final copyedits (#1165) cleanup, typos, revert to US spelling etc. | 29 November 2019, 11:41:51 UTC |
a492858 | Artem Artemev | 26 November 2019, 23:29:31 UTC | Fix printing test (#1166) | 26 November 2019, 23:29:31 UTC |
bd1eb7c | Fergus | 26 November 2019, 20:55:57 UTC | Assign lower bound directly to likelihood variance. (#1162) | 26 November 2019, 20:55:57 UTC |
1b9073d | st-- | 26 November 2019, 20:54:33 UTC | Fixes #1080 by casting tensorflow dtypes to numpy dtypes (#1164) | 26 November 2019, 20:54:33 UTC |
4654676 | Artem Artemev | 26 November 2019, 20:54:00 UTC | ELBO and log marginal likelhood of the SVGP has one data argument (#1163) | 26 November 2019, 20:54:00 UTC |
7bf3bf7 | st-- | 21 November 2019, 17:42:28 UTC | minor docstring improvement (#1161) | 21 November 2019, 17:42:28 UTC |
89a0bfb | Eric Hammy | 21 November 2019, 16:48:50 UTC | quick fix of documentation mathematics (#1155) * quick fix of documentation mathematics * Apply suggestions from code review much clearer Co-Authored-By: st-- <st--@users.noreply.github.com> | 21 November 2019, 16:48:50 UTC |
6a1abd4 | Joe Hall | 21 November 2019, 16:09:52 UTC | Porting the generalized periodic kernel (#1158) Turns the Periodic kernel into a wrapper-kernel that takes any Stationary kernel as an argument `base` and turns it into a periodic version. Backwards-incompatible but more flexible and less code! | 21 November 2019, 16:09:52 UTC |
9cdb2a2 | Joe Hall | 21 November 2019, 14:33:38 UTC | Add config option for positive bijector + re-introduce positive lower bound (#1148) | 21 November 2019, 14:33:38 UTC |
3af7b8e | Mark van der Wilk | 19 November 2019, 11:15:13 UTC | Stabilise upper bound of `SGPR`. (#1159) | 19 November 2019, 11:15:13 UTC |
59ef09c | Artem Artemev | 16 November 2019, 13:13:56 UTC | Bug fix in mcmc.ipynb (#1157) | 16 November 2019, 13:13:56 UTC |
52e3f61 | Joe Hall | 16 November 2019, 11:28:41 UTC | ARD and Stationaries Refactor (#1088) | 16 November 2019, 11:28:41 UTC |
78238bd | Artem Artemev | 14 November 2019, 15:23:18 UTC | Prepare release 2.0.0-rc1 (#1153) | 14 November 2019, 15:23:18 UTC |
473e9bc | Eric Hammy | 14 November 2019, 12:23:17 UTC | Update contributors (#1152) | 14 November 2019, 12:23:17 UTC |
5ec3260 | Artem Artemev | 14 November 2019, 12:22:56 UTC | Update README (#1151) | 14 November 2019, 12:22:56 UTC |
624ed39 | Artem Artemev | 14 November 2019, 11:54:53 UTC | Gaussian process with neural network notebook (#1149) | 14 November 2019, 11:54:53 UTC |
32b76b7 | Artem Artemev | 14 November 2019, 11:05:48 UTC | Update CircleCI config (#1150) | 14 November 2019, 11:05:48 UTC |
a241dd3 | Eric Hammy | 13 November 2019, 23:25:50 UTC | Missing `full_output_cov` in VGP and GPLVM parameter prevents us from calling, `predict_f_samples` from the base class.. (#1147) | 13 November 2019, 23:25:50 UTC |
24b5733 | Eric Hammy | 13 November 2019, 12:27:36 UTC | Migrate MCMC notebook to gpflow2.0 (#1100) Migrate MCMC notebook to gpflow 2 using tensorflow probabilities. Changes required a few changes across the rest of the codebase, outside of the notebook. * small change to leaf printing function (fix bug, which was preventing printing of composite kernels) * parameters and trainable_parameters now return tuples, not generators, like tf implementation of variables, trainable_variables * tfp.distributions now work with different dtypes (by wrapping of parameters), so now play nicely with gpflow. | 13 November 2019, 12:27:36 UTC |
046b107 | Eric Hammy | 13 November 2019, 10:36:58 UTC | Create autodocumentation of API for GPFflow. (#1120) The script generate_rst.py creates a folder `gpflow` which contains all the rst for the autogeneration using sphinx. Also added is type checking to the documentation and css and logo for the docs. | 13 November 2019, 10:36:58 UTC |
1a38796 | Sergio Pascual | 12 November 2019, 15:24:54 UTC | Updated contributors (#1128) | 12 November 2019, 15:24:54 UTC |
0cadb9e | Artem Artemev | 12 November 2019, 14:24:53 UTC | Remove persistent tape fixing #1142 (#1145) | 12 November 2019, 14:24:53 UTC |
f282e01 | Joe Hall | 12 November 2019, 13:06:18 UTC | Minor fix in README.md (#1143) | 12 November 2019, 13:06:18 UTC |
ff339f8 | Vincent Dutordoir | 11 November 2019, 15:09:48 UTC | Updated mixture_density_network notebook (#1141) | 11 November 2019, 15:09:48 UTC |
4cf768f | Vincent Dutordoir | 11 November 2019, 12:38:25 UTC | Update notebook tests (#1140) | 11 November 2019, 12:38:25 UTC |
732f114 | Vincent Dutordoir | 09 November 2019, 19:23:36 UTC | Deprecate neg_log_marginal_likelihood (#1139) | 09 November 2019, 19:23:36 UTC |
96940dd | Artem Artemev | 09 November 2019, 18:10:12 UTC | Computation of the gradient must be outside of the GradientTape | 09 November 2019, 18:10:12 UTC |
c13c49a | Artem Artemev | 09 November 2019, 13:40:48 UTC | Refactor config with a dataclass (#1135) | 09 November 2019, 13:40:48 UTC |
157aa4f | Vincent Dutordoir | 08 November 2019, 17:16:48 UTC | Update custom mean function (#1134) | 08 November 2019, 17:16:48 UTC |
637534a | Artem Artemev | 08 November 2019, 14:05:14 UTC | Fix a bug for slice cov when tf.function(autograph=False) applied. (#1136) | 08 November 2019, 14:05:14 UTC |
d05f429 | Vincent Dutordoir | 08 November 2019, 13:41:48 UTC | Use experimental_ref when using tf.Variable as key in Dicts (#1132) | 08 November 2019, 13:41:47 UTC |
015975e | Vincent Dutordoir | 07 November 2019, 14:01:37 UTC | Fig importing bug in changepoints kernel (#1133) | 07 November 2019, 14:01:37 UTC |