Ktrain

New:
- N/A

Changed
- Fixes to address changes or issues in TensorFlow 2.2.0:
- created `metrics_from_model` function due to changes in the way metrics are extracted from compiled model
- use `loss_fn_from_model` function due to changes in they way loss functions are extracted from compiled model
- addd `**kwargs` to `AdamWeightDecay based on [this issue](https://github.com/tensorflow/addons/issues/1645)
- changed `TransformerTextClassLearner.predict` and `TextPredictor.predict` to deal with tuples being returned by `predict` in TensorFlow 2.2.0
- changed multilabel test to use loss insead of accuracy due to [TF 2.2.0 issue](https://github.com/tensorflow/tensorflow/issues/41114)
- changed `Learner.lr_find` to use `save_model` and `load_model` to restore weights due to [this TF issue](https://github.com/tensorflow/tensorflow/issues/41116)
and added `TransformersPreprocessor.load_model_and_configure_from_data` to support this

Fixed:
- N/A

New:
- N/A

Changed
- N/A

Fixed:
- Explicitly supply `'truncate='longest_first'` to prevent sentence pair classification from breaking in `transformers==3.0.0`
- Fixed typo in `encode_plus` invocation

New:
- N/A

Changed
- N/A

Fixed:
- Explicitly supply `'truncate='longest_first'` to prevent sentence pair classification from breaking in `transformers==3.0.0`

New:
- N/A

Changed
- N/A

Fixed:
- Changed `setup.py` to open README file using `encoding="utf-8"` to prevent installation problems on Windows machines with `cp1252` encoding

New:
- Added support for Russian in `text.EnglishTranslator`

Changed
- N/A

Fixed:
- N/A

New:
- N/A

Changed
- N/A

Fixed:
- Properly set device in `text.Translator` and use cuda when available