Cross Validation, Grid Search and Random Search for TensorFlow 2 Datasets
MIT License
Bot releases are visible (Hide)
Published by franneck94 12 months ago
Published by franneck94 over 1 year ago
Published by franneck94 about 2 years ago
Published by franneck94 about 2 years ago
Published by franneck94 about 3 years ago
Published by franneck94 about 3 years ago
Published by franneck94 almost 4 years ago
Added support for TensorFlow 2.0+ (previously only 2.3)
Bug fix in CrossValidation search, by replacing the parameter name train_dataset
with dataset
.
Published by franneck94 almost 4 years ago
Updated Version number, due to missing update in last release.
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.
Published by franneck94 almost 4 years ago
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.
Published by franneck94 almost 4 years ago
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.
Published by franneck94 almost 4 years ago
Bugfixes of version 0.1.3.
Published by franneck94 almost 4 years ago
Bugfixes of version 0.1.2.
Published by franneck94 almost 4 years ago
Bugfixes of version 0.1.1.
Removed docs from this repo.
Correct usage of find_package in setup.py.
Published by franneck94 almost 4 years ago
Bugfixes of the release 0.1.0
Published by franneck94 almost 4 years ago
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.
Published by franneck94 almost 4 years ago