Ktrain

New:
- N/A

Changed:
- `MultiArrayDataset` accepts list of Numpy arrays

Fixed:
- fixed incorrect activation in `TextPredictor` for multi-label Transformer models
- fixed `top_losses` for regression tasks

New:
- initial base `ktrain.Dataset` class for use as a Sequence wrapper to better support custom datasets/models

Changed:
- N/A

Fixed:
- N/A

New:
- N/A

Changed:
- N/A

Fixed:
- fix to support multilabel text classification in `Transformers`
- `_prepare_dataset` no longer breaks when validation dataset has not been supplied

New:
- availability of a new, simplied interface to Hugging Face transformer models
- added 'distilbert' as an available model in `text.text_classifier` function

Changed:
- `preproc` argument is required for `text.text_classifier`

Fixed:
- `core._load_model` calls `_make_predict_function` before returning model
- added warning when non-adam optimizer is used with `cycle_momentum=True`

New:
- N/A

Changed:
- N/A

Fixed:
- Fixed error when using *ktrain* with v0.2.x of `fastprogress`. *ktrain* can now be used with both v0.1.x and v0.2.x of `fastprogress`

New:
- All data-loading functions (e.g., `texts_from_csv`) accept a `random_state` argument
that will enable consistent reproduction of the train-test split.

Changed:
- perform local checks for `stellargraph` where needed.
- removed `stellargraph` as dependency due to issues with it overwriting `tensorflow-gpu`
- change `setup.py` to skip navigation links for pypi page

Fixed:
- N/A