Commit message (Collapse) | Author | Age | |
---|---|---|---|
* | Modify docs under contrib/distributions to point to tfp. | Brian Patton | 2018-09-20 |
| | | | | PiperOrigin-RevId: 213866466 | ||
* | Move from deprecated self.test_session() to self.cached_session(). | A. Unique TensorFlower | 2018-09-17 |
| | | | | | | | | self.test_session() has been deprecated in 9962eb5e84b15e309410071b06c2ed2d6148ed44 as its name confuses readers of the test. Moving to cached_session() instead which is more explicit about: * the fact that the session may be reused. * the session is not closed even when doing a "with self.test_session()" statement. PiperOrigin-RevId: 213326581 | ||
* | Remove magic-doc-links from code. | Mark Daoust | 2018-08-16 |
| | | | | | | | | | | This change contains no code changes. Only doc-strings. We can't use relative links in code files, so we don't have much choice but to link to tensorflow.org/ The deleted links were to docs that no longer exist. PiperOrigin-RevId: 209019572 | ||
* | Fix Missing r-string. | Mark Daoust | 2018-06-28 |
| | | | | | | | | | | The docs generator is not happy about the "\a" in "\approx" is becoming a "alert" escape sequence. This should also fix a lot of the mathjax rendering on this page: https://www.tensorflow.org/api_docs/python/tf/contrib/bayesflow/monte_carlo/expectation PiperOrigin-RevId: 202550662 | ||
* | Gamma distribution and the derived distributions (Beta, Dirichlet, Student's ↵ | A. Unique TensorFlower | 2018-06-22 |
| | | | | | | | | | | | | | | | t, inverse Gamma) are fully reparameterized. For every distribution, the changes are: * Set reparameterization_type to FULLY_REPARAMETERIZED. * Add a note about reparameterization and an example to the docstring. * Add a test that ensures that the gradients exist. Additional changes: * Fix docstring and test in TFP that assume that Gamma is not reparameterized. We simply replace Gamma with Bernoulli :) * Fix paths to modules in docstrings. PiperOrigin-RevId: 201691205 | ||
* | Remove Bayesflow/Distribution/Bijector docs. | A. Unique TensorFlower | 2018-06-11 |
| | | | | | | These docs are out of date. PiperOrigin-RevId: 200066984 | ||
* | Merge changes from github. | Yifei Feng | 2018-04-23 |
| | | | | PiperOrigin-RevId: 194031845 | ||
* | Merge changes from github. | Michael Case | 2018-04-10 |
| | | | | PiperOrigin-RevId: 192388250 | ||
* | Remove all_opensource_files. It's not needed any more. | Martin Wicke | 2018-03-28 |
| | | | | PiperOrigin-RevId: 190878279 | ||
* | Finish deprecation of tf.contrib.bayesflow.{HMC,MetropolisHastings}. | Joshua V. Dillon | 2018-03-26 |
| | | | | | | New home: https://github.com/tensorflow/probability/tree/master/tensorflow_probability/python/mcmc PiperOrigin-RevId: 190560180 | ||
* | Add custom_gradient function. | Joshua V. Dillon | 2018-03-12 |
| | | | | PiperOrigin-RevId: 188765271 | ||
* | Improve usability of `tf.contrib.bayesflow.custom_gradient` by removing need ↵ | Joshua V. Dillon | 2018-03-12 |
| | | | | | | for `axis` arg and support taking lists. PiperOrigin-RevId: 188751894 | ||
* | Migrate tf.contrib.bayesflow.optimizers to tfp.optimziers. | Joshua V. Dillon | 2018-03-09 |
| | | | | PiperOrigin-RevId: 188547477 | ||
* | Migrate AIS chain into `tfp.mcmc` and modularize its interface to take a ↵ | Joshua V. Dillon | 2018-03-07 |
| | | | | | | TransitionKernel. PiperOrigin-RevId: 188239559 | ||
* | Move `tf.contrib.bayesflow.layers` to `tfp.layers`. | Joshua V. Dillon | 2018-03-07 |
| | | | | PiperOrigin-RevId: 188203941 | ||
* | Migrate Halton Sequence sampler into tensorflow_probability. | Joshua V. Dillon | 2018-03-07 |
| | | | | PiperOrigin-RevId: 188191091 | ||
* | Docs: Fix prefix for the fancy-linker. | Billy Lamberta | 2018-03-06 |
| | | | | PiperOrigin-RevId: 188075262 | ||
* | Migrate MCMC diagnostics and Halton Sequence sampler into | Joshua V. Dillon | 2018-03-06 |
| | | | | | | tensorflow_probability. PiperOrigin-RevId: 188057302 | ||
* | disabling msan flaky test | Olivia Nordquist | 2018-03-05 |
| | | | | PiperOrigin-RevId: 187942643 | ||
* | Add objective functions for variational inference with Csiszar f-divergences. | A. Unique TensorFlower | 2018-03-05 |
| | | | | PiperOrigin-RevId: 187931921 | ||
* | Automated g4 rollback of changelist 185073515 | A. Unique TensorFlower | 2018-03-05 |
| | | | | PiperOrigin-RevId: 187852929 | ||
* | Add util which creates Python callable with tf.Variables explicitly as | Joshua V. Dillon | 2018-03-01 |
| | | | | | | arguments. PiperOrigin-RevId: 187561302 | ||
* | Internal change. | Jeremy Lau | 2018-02-26 |
| | | | | PiperOrigin-RevId: 187061863 | ||
* | Internal change. | Jeremy Lau | 2018-02-23 |
| | | | | PiperOrigin-RevId: 186843326 | ||
* | Unify metropolis_hastings interface with HMC kernel. | Dustin Tran | 2018-02-22 |
| | | | | PiperOrigin-RevId: 186716023 | ||
* | Automated g4 rollback of changelist 186260342 | Dustin Tran | 2018-02-20 |
| | | | | PiperOrigin-RevId: 186393300 | ||
* | DOCFIX: hmc.sample_chain kwarg num_steps_between_results docstring seemed to | Ian Langmore | 2018-02-20 |
| | | | | | indicate a different type of thinning than what is actually going on. PiperOrigin-RevId: 186349630 | ||
* | Automated g4 rollback of changelist 186260342 | Dustin Tran | 2018-02-19 |
| | | | | PiperOrigin-RevId: 186266857 | ||
* | Reduce tfp.layers boilerplate via programmable docstrings. | Dustin Tran | 2018-02-19 |
| | | | | PiperOrigin-RevId: 186260342 | ||
* | effective_sample_size kwarg change (same default behavior). | Ian Langmore | 2018-02-14 |
| | | | | | | | | | * rename max_lags --> filter_beyond_lag * rename max_lags_threshold --> filter_threshold * Users can use both filters, and they combine in an "OR" manner * None ==> turn off a filter. PiperOrigin-RevId: 185666926 | ||
* | Disable flaky halton_sequence_test | A. Unique TensorFlower | 2018-02-11 |
| | | | | PiperOrigin-RevId: 185294455 | ||
* | Automated g4 rollback of changelist 185073515 | A. Unique TensorFlower | 2018-02-10 |
| | | | | PiperOrigin-RevId: 185246348 | ||
* | TEST: test of kernel_results added to hmc_test.py | Ian Langmore | 2018-02-09 |
| | | | | PiperOrigin-RevId: 185191871 | ||
* | Extended the Halton sequences to support randomization. Implemented the ↵ | A. Unique TensorFlower | 2018-02-08 |
| | | | | | | randomization scheme described in arXiv:1706.02808. PiperOrigin-RevId: 185073515 | ||
* | Add effective_sample_size to tf.contrib.bayesflow.mcmc_diagnostics. | Ian Langmore | 2018-02-08 |
| | | | | | | Also, start dealing with list args in a more regular manner. PiperOrigin-RevId: 185032115 | ||
* | Automated g4 rollback of changelist 184551259 | Joshua V. Dillon | 2018-02-06 |
| | | | | PiperOrigin-RevId: 184738583 | ||
* | Add utility function which makes implicit `tf.get_variable` dependencies an | Joshua V. Dillon | 2018-02-06 |
| | | | | | | explicit argument of a callable. PiperOrigin-RevId: 184725878 | ||
* | mcmc_diagnostics.py added to contrib/bayesflow/. potential_scale_reduction ↵ | Ian Langmore | 2018-02-06 |
| | | | | | | | | function added. . PiperOrigin-RevId: 184644450 | ||
* | Automated g4 rollback of changelist 184323369 | Joshua V. Dillon | 2018-02-05 |
| | | | | PiperOrigin-RevId: 184551259 | ||
* | Breaking change: Revise HMC interface to accept a list of Tensors ↵ | Joshua V. Dillon | 2018-02-02 |
| | | | | | | representing a partitioning of chain state. PiperOrigin-RevId: 184323369 | ||
* | Internal change. | Anna R | 2018-02-01 |
| | | | | PiperOrigin-RevId: 184194895 | ||
* | Add C0301 line-too-long error to pylint sanity check. | Yifei Feng | 2018-01-26 |
| | | | | PiperOrigin-RevId: 183467186 | ||
* | Move layers_dense_variational_impl.py to layers_dense_variational.py. | Dustin Tran | 2018-01-19 |
| | | | | PiperOrigin-RevId: 182568201 | ||
* | Add convolutional Flipout layers. | Dustin Tran | 2018-01-19 |
| | | | | PiperOrigin-RevId: 182559534 | ||
* | Merge changes from github. | Patrick Nguyen | 2017-12-28 |
| | | | | PiperOrigin-RevId: 180301735 | ||
* | Internal change. | Anna R | 2017-12-21 |
| | | | | PiperOrigin-RevId: 179866603 | ||
* | Adding an optimizer module for ConstantSGD. | A. Unique TensorFlower | 2017-12-20 |
| | | | | PiperOrigin-RevId: 179703560 | ||
* | Add probabilistic convolutional layers. | Dustin Tran | 2017-12-18 |
| | | | | PiperOrigin-RevId: 179490700 | ||
* | Add DenseFlipout probabilistic layer. | Dustin Tran | 2017-12-18 |
| | | | | PiperOrigin-RevId: 179310861 | ||
* | Restandardize `DenseVariational` as simpler template for other probabilistic ↵ | Dustin Tran | 2017-12-15 |
| | | | | | | layers. PiperOrigin-RevId: 179255435 |