Tiramisu-brulee

-------------------

* Add commit hash logger function to tag MLFlow runs
* Save configuration files to MLFlow
* Add option to save top K checkpoints

-------------------

* Add union and voting aggregation to prediction and other minor bug fixes

-------------------

* Reformat with newer version of black (v21.7b0)
* Change to ``every_n_epochs`` in ``ModelCheckpoint`` since ``every_n_val_epochs`` will be deprecated

-------------------

* Detect and use tensorboard directory (``/opt/ml/output/tensorboard``) for logging on SageMaker

-------------------

* Add experiment and trial name as options to explicitly specify artifact locations

-------------------

* Change AWS option to just MLFlow
* Compliant with mypy
* Other minor bug fixes and fix docs