Psiz

Patch for loading old models. Changed deprecated variable use in active selection generator. Reworked preprocess module. Reworked visualize module to more closely align with Matplotlib conventions. Added timing information to verbose output for psiz.models.fit, psiz.models.posterior_samples and psiz.generators.generate methods.

Patch for evaluate method.

Updated getter/setter API.
Setting variables now uses a flatter dot-notation syntax. The trainability of parameters is modified using the `trainable` method which replaces `freeze` and `thaw`.

Initial alpha release
This alpha release contains all of the core functionality necessary for inferring psychological embeddings and reproducing the results of the paper "Obtaining psychological embeddings through joint kernel and metric learning" (Roads & Mozer, in press).

This release relies on TensorFlow 1.14. The code base is gradually being moved towards Tensorflow 2.0. Once Tensorflow 2.0 is officially released, a new release of this package will be made.