Pytorch-toolbelt

* Fixes to CI actions
* Adding support for python 3.10
* Bugfix in DatasetMeanStdCalculator when mask argument was used

Breaking Changes
All catalyst-related callbacks are moved to [fork](https://github.com/BloodAxe/catalyst) of the Catalyst library

Bugfixes

- Fix https://github.com/BloodAxe/pytorch-toolbelt/issues/78 thanks https://github.com/mehran66 for pointing this out

New Stuff

- InriaAerialImageDataset for working with Inria Aerial Dataset
- `get_collate_for_dataset` function to get collate fn if a dataset instance (argument) exposes `get_collate_fn` method. Works also for ConcatDataset.

Improvements

- `DatasetMeanStdCalculator` supports `dtype` to specify accumulator type (float64 by default)

BugFixes

* Fixed bug in `ApplySoftmaxTo` and `ApplySigmoidTo` modules that could lead to activations not applied to input when it was a string

New API

* Added `fs.find_images_in_dir_recursive`
* Added `utils.describe_outputs` to return a human-friendly representation of complex (dict, nested list, etc) outputs to see shape, mean/std of each tensor.

Other

More MyPy fixes & type annotations