v0.3.3

New features

• Added set_cache_maxsize, a setter of maxsize for lru_cache, and cache_maxsize, a getter of maxsize for lru_cache. By increasing this maxsize, the size that can store the results of get_params (≒ forward of the Distribution class) becomes larger. This will speed up most VAE implementations!
• Added the mixture of experts (MoE)

Bug fix

• Fixed get_params for replace_var
• Fixed maxsize of lru_cache for get_params
• Fixed a major bug in PoE.

v0.3.2

New features

• Added description of tutorial in readme. #167
• Added save and load methods to Model class. #161
• Added an option to replace the graphical model with a deterministic one. #169

Bug fix

• Fixed the Bernoulli Distribution so that the likelihood calculation of continuous values such as luminance is also available in the new version of pytorch.
• Fixed a bug where the option feature_dims, which determines whether tensor dimensions are added together as simultaneous log likelihoods, was not enabled. #163
• Resolved the issue where options set in DistGraph.set_option were overwritten by options in Distribution.sample and were not reflected. #162
• Avoided build failures with readthedocs. #170

v0.3.1

New feature

• Added installation instructions through Docker Hub to Readme #157
• Allowed scalar type parameters of DistributionBase #159

Bug fix

• Reduced dependent libraries (tensorboardX, tqdm, torchvision) #156
• Fixed build error in travis CI and fixed travis badge link in Readme #156
• Fixed error in pytest (ignored tutorial directory) #156
• Typo fix of tutorials #160

v0.3.0

New feature

• New field distribution.graph represents graphical model of the distribution. #119
• Supported drawing a grapical model by networkx.draw_networkx(distribution.graph.visible_graph()). #122
• Added tutorial notebooks. #148
  Enabled memoization for calcuration graph of pixyz to speed up. #149

Changed API

• Renamed DataDistribution to EmpiricalDistribution. #146
• timestep_var is no longer specified by default (t is still the default in the display), which gives the time index when evaluating step loss or calling SliceStep. #142
• Corrected the error of the time index in the display. #142
• Reverted the TransformedDistribution arguments to their previous (=v0.1.4) format (Inference in TransformedDistribution internally uses the result of the sample / forward called immediately before). #139
• Removed the input_var argument of the Loss API. #150
• Added the ConstantVar class that sets the value of a variable before calling loss.eval. #150
• The argument order of var and cond_var in Distribution API has been unified. (Var first) #147
• Changed the output directory of example notebooks to make it easier to browse (and automatically installed sklearn with !pip). #141

Bug fix

• Eliminated of errors in pytorch 1.6 caused by flow's non-contiguous tensors. #140
• Fixed bug related to documents. #138
• Fixed a bug so that PoE does not cause an error when only one distribution is specified. #144
• Fixed a bug when specifying the same random variable as args of init in DistributionBase. #143
• Replaced forward call with __call__ call to take advantage of pytorch.nn.module hook options. #136

v0.2.1

Updates

• #133 Enabled to use time-specific step losses without extension of slice function
• #127, #130 Changed the output directory of example notebooks to make it easier to browse (and automatically installed sklearn with !pip)
• #126 Reverted the TransformedDistribution arguments to their previous format (use memoization to get the log-likelihood)

Bugfix

• #134 Elimination of errors in the latest version of pytorch caused by flow non-contiguous tensors
• #133 Fixed a bug related to timestep_var in Iterative Loss
• #132 Fixed a bug when specifying the same random variable as args of init in DistributionBase
• #124 Fixed a bug so that PoE does not cause an error when only one distribution is specified

v0.2.0

Interface change 🛠︎
Bug Fixes 🐛
Added a feature 🆕

Distribution API

• 🛠︎Change the argument order of __init__ in the exponential distribution families and make the distribution parameters explicit #90
• 🛠︎Removed the sampling option from DistributionBase.set_dist (relaxed distribution families still have a sampling option) #108
• 🛠︎ TransformedDistribution will be the probability distribution of 2 variables of input and output of flow, and the return_all option of the conventional sample method is abolished. #115
• 🛠︎ Rename return_all option of InverseTransformedDistribution.sample to return_hidden #115
• 🛠︎ Added TransformedDistribution(or InverseTransformedDistribution ).sample with return_all option (that is, option that also returns random variables that are not involved). #115
• 🛠︎ TransformedDistribution.__init__ argument var is renamed toflow_output_var
• 🆕 Added Distribution.has_reparam property #93
• 🆕 Add return_all option to MixtureModel.sample #115
• 🐛 Fixed a bug that unintentional overwrite of parameters of basic Distribution when torch.load #113

Loss API

• 🛠︎StochasticReconstructionLoss removed (need to explicitly configure this loss) #103
• 🛠︎Changed the base class of Loss to torch.nn.Module #100
• 🛠︎Renamed Loss.train to Loss.loss_train, and Loss.test to Loss.loss_test #100
• 🛠︎Renamed Loss._get_eval to Loss.forward #95
• 🛠︎Added Entropy method to switch entropy estimation by AnalyticalEntropy and MonteCarlo in options (deprecated Entropy class) #89
• 🛠︎Added a CrossEntropy method that can be switched as well (deprecated the CrossEntropy class) #89
• 🛠︎Added a KullbackLeibler method that can be switched as well (deprecated the KullbackLeibler class) #89
• 🛠︎ deprecated ELBO class and replaced it with ELBO method that returns a Loss instance #89
• 🆕 Support for Loss.detach method #93
• 🆕 Support for MinLoss, MaxLoss #95
• 🆕 Support for alternative loss REINFORCE to derive a policy gradient. #93
• 🆕 Loss support for DataParallel #100
• 🆕 Separated some features of the Loss class into the Divergence class #95
• 🆕 Added return_all option to Loss.eval (that is, when return_dict = True, you can also select whether to return unrelated random variables) #115
• 🐛 Fixed a bug in IterativeLoss where the past value was conditioned on each step as the future value. #115
• 🐛 Placed the parameter tensor of ValueLoss in nn.Module.device. #100
• 🐛 Fixed incorrect argument checking in WassersteinDistance and MMDLoss. #103
• 🐛 Fixed a bug in checking variables in Loss initialization #107
• 🐛 Fixed a bug in IterativeLoss #107

Other

• 🆕 Add utils.lru_cache_for_sample_dict decorator that enables memoization with a function that takes a dictionary of random variables and their realization values ​​ #109
• 🆕 Renamed examples/vae_model to vae_with_vae_class
• 🆕 Added some exception messages #103
• 🐛 Fixed jacobian calculation in flow/Preprocess #107
• 🐛 Fixed a bug in some browsers that does not show the formula of readme.
• 🐛 Alternate text is displayed when readme formula is not displayed. #117

v0.1.4

• Fixed some bugs (#106)
• StochasticReconstructionLoss became obsolete (#103)
• Fixed a bug in IterativeLoss (#102)

v0.1.3

• Fix some bugs
• Support the sample_shape argument of the Expectation class. (#88 )

v0.1.2

Updates

• Add a new example notebook mvae.ipynb including the MIVAE implementation (see #80).
• Rename mvae_poe.ipynb to jmvae_poe.ipynb to avoid confusion (see #80).

Bugfix

• Fix some exception-related bugs (#81, #83).
• Fix a typo in README (#82).

v0.1.1

Bug Fix

• Fix the specified version of pytorch in install_requires.