Ml4ir

Latest version: v0.1.16

Safety actively analyzes 706267 Python packages for vulnerabilities to keep your Python projects secure.

Page 2 of 3

Changed

- Adding all trained features to serving parse fn by default

Changed

- Refactored secondary label metrics computation for ranking and added unit tests
- Added NDCG metric for secondary labels

Added

- New argument to model.save()

Added

- SoftmaxCrossEntropy loss for ranking models

Fixed

- Fixing required arguments in setup.py

Added

- Adding support for performing post-training steps (such as copying data) by custom class inheriting RelevancePipeline.

Has known vulnerabilities

Previous Next