Submodule | Maintainers | Contact Info |
---|---|---|
cohens_kappa | Aakash Nain | [email protected] |
f_scores | Saishruthi Swaminathan | [email protected] |
r_square | Saishruthi Swaminathan | [email protected] |
multilabel_confusion_matrix | Saishruthi Swaminathan | [email protected] |
Submodule | Metric | Reference |
---|---|---|
cohens_kappa | CohenKappa | Cohen's Kappa |
f1_scores | F1 micro, macro and weighted | F1 Score |
r_square | RSquare | R-Sqaure |
multilabel_confusion_matrix | Multilabel Confusion Matrix | mcm |
In order to conform with the current API standard, all metrics must:
- Inherit from
tf.keras.metrics.Metric
. - Register as a keras global object so it can be serialized properly.
- Add the addon to the
py_library
in this sub-package's BUILD file.
- Simple unittests that demonstrate the metric is behaving as expected.
- When applicable, run all unittests with TensorFlow's
@run_in_graph_and_eager_modes
(for test method) orrun_all_in_graph_and_eager_modes
(for TestCase subclass) decorator. - Add a
py_test
to this sub-package's BUILD file.
- Update the table of contents in this sub-package's README.