GPflow

Release 1.0.0

Main features and improvements

• Clear and aligned with tree-like structure of GPflow models design.
• GPflow trainable parameters are no longer packed into one TensorFlow variable.
• Integration of bare TensorFlow and Keras models with GPflow became very simple.
• GPflow parameter wraps multiple tensors: unconstained variable, constrained tensor and prior tensor.
• Instantaneous parameter's building into the TensorFlow graph. Once you created an instance of parameter, it creates necessary tensors at default graph immediately.
• New implementation for AutoFlow. autoflow decorator is a replacement.
• GPflow optimizers match TensorFlow optimizer names. For e.g. gpflow.train.GradientDescentOptimizer mimics tf.train.GradientDescentOptimizer. They even has the same instantialization signature.
• GPflow has native support for Scipy optimizers - gpflow.train.ScipyOptimizer.
• GPflow has advanced HMC implementation - gpflow.train.HMC. It works only within TensorFlow memory scope.
• Tensor conversion decorator and context manager designed for cases when user needs to implicitly convert parameters to TensorFlow tensors: gpflow.params_as_tensors and gpflow.params_as_tensors_for.
• GPflow parameters and parameterized objects provide convenient methods and properties for building, intializing their tensors. Check initializables, initializable_feeds, feeds and other properties and methods.
• Floating shapes of parameters and dataholders without re-building TensorFlow graph.

Note

This release is not backward compatible with previous versions.

Major updates:

• Bug fix for log_jacobian in transforms.
• Different variants of gauss_kl_* are now deprecated in favour of a unified gauss_kl implementation.

NOTE: Next release will have breaking changes and not backward compatible.

Major features and improvements:

• Rename python package name to gpflow.
• Compile function has external session and graph arguments.
• Tests use Tensorflow TestCase class for proper session managing.

Minor updates, mostly to keep up with the tensorflow API.

This works with tensorflow 0.9.0