Version 2.0.0: May 20, 2024

• This will be the stable version for TF 2.13+ which is the first version that supports keras 3.0

Version 1.0.0: October 29, 2023

• Some rework, updates docs and versioning. This will be the stable version for TF (Keras) 2.8+ and Python 3.9+

Version 0.4.4: March 13, 2023

• Bugfix for MacOS tensorflow metal

Changelog

• Bugfix for computing the mean score in CV

Release 0.4.2

• Bugfix for detecting if the mode is either minimize the loss or maximize the metric

Version 0.4.1: September 11, 2021

• Added detailed information to docstrings
• The summary method now returns the printed string, such that it can be stored to a file
• Now also exporting the dataset_join function

Changes

• Updated TF Version

Features

Added support for TensorFlow 2.0+ (previously only 2.3)

Bug FIxes

Bug fix in CrossValidation search, by replacing the parameter name train_dataset with dataset.

Changes in Release 0.2.1

Updated Version number, due to missing update in last release.

New Features from Release 0.2.0

Implemented the GridSearchCV and RandomSearchCV.
ALso implemented a modification of the TensorBoard callback to store the model
results of each parameter combination in a distinct sub-sir.

New Features

Implemented the GridSearchCV and RandomSearchCV.
ALso implemented a modification of the TensorBoard callback to store the model
results of each parameter combination in a distinct sub-sir.

New Features

Implemented the first draft of the GridSearchCV and RandomSearchCV.
However, one important part is missing.
The sliding validation fold over the dataset.
Currently for every fold, the same subset for the validation is used.
This will be implemented for the final 0.2.0 release.

Bugfixes of version 0.1.3.

Bugfixes of version 0.1.2.

Bugfixes of version 0.1.1.
Removed docs from this repo.
Correct usage of find_package in setup.py.

Bugfixes of the release 0.1.0

Notes

In this first official release, the GridSearch and RandomSearch with a validation srt is implemented.
In the next minor release (0.2.0) the CrossValidation variant of these searches will be implemented.