paradime - v1.1.0

Changes

This version aligns the ParaDime codebase with the state described in the revised paper preprint. This includes mostly changes to the specifications and their parsing:

• introduced registration functions
• moved parsing functionality to main module
• minor fixes in the docs

- Python
Published by einbandi about 3 years ago

paradime - v1.0.0

Changes

• Restructured ParaDime routines:
  • Losses are now added as a dict and referenced in training phases.
  • Data can be registered earlier, but that is no longer required. Instead data is added in the train call.
• Added specification parser (ParametricDR.from_spec).
• Added new examples and improved docs.

- Python
Published by einbandi over 3 years ago

paradime - v0.3.3

Changes

• Removed PyTorch from the dependencies. It must now be installed separately.
• Updated docs to reflect installation changes.
• Improved loss tracking for compound losses.
• Scatterplot now accepts an axes object.
• Added various examples to the docs.

- Python
Published by einbandi over 3 years ago

paradime - v0.3.1

Changes

• Dependencies are now installed automatically.
• Fixed a bug with the color pallette that broke the scatterplot function.

- Python
Published by einbandi over 3 years ago

paradime - v0.3.0

Changes

• Changed syntax for data_key in relations, to allow computation of global relations for different attributes of the data set.
• Added parameters for model methods to be used by losses.
• Various bugfixes.
• Improved docs and switched to nbsphinx for examples.

- Python
Published by einbandi over 3 years ago

paradime - v0.2.0

Changes

• Many bugfixes
• Refactored utils
• Switched to logging module
• Added first example script
• Added most important info to docs

- Python
Published by einbandi over 3 years ago

paradime - v0.1.1

First release. Base functionality is finished. Documentation is still rudimentary. Examples are missing completely (apart from some in the playground notebook).

# Expected Major Changes

• ParametricDR API mostly stable, but minor changes with respect to declaration of training phases and/or datasets are expected.
• Possible refactoring/renaming of methods used as loss_function in Loss instances.

- Python
Published by einbandi over 3 years ago