Swin Transformer notebook

[dnth]

This PR adds a notebook to show users how to use Swin Transformer as backbone for the RetinaNet and VFNet model.

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[codecov]

Codecov Report

Merging #1059 (8e16bdd) into master (4a8f52d) will not change coverage.
The diff coverage is n/a.

@@           Coverage Diff           @@
##           master    #1059   +/-   ##
=======================================
  Coverage   85.96%   85.96%           
=======================================
  Files         283      283           
  Lines        5944     5944           
=======================================
  Hits         5110     5110           
  Misses        834      834           

Flag	Coverage Δ
unittests	85.96% <ø> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 4a8f52d...8e16bdd. Read the comment docs.

[FraPochetti]

Hey @dnth thanks a lot man!
Would you mind reverting the changes you made to the getting_started notebook?
notebooks/getting_started_object_detection.ipynb
There are a couple of tweaks that I don't think are needed for this PR, e.g. adding the Swin notebook.

Also, feel free to add the Swin notebook to the Other tutorials section of the docs, here.
It'd be cool to have it there!

[ai-fast-track]

Thanks a lot @dnth!

To add the new notebooks to the Docs as @FraPochetti suggested, all you need is to add this line :

    - Using Swin Transformer as Backbone: using_swin_transformer_as_backbone.ipynb.md

after this line:
https://github.com/dnth/icevision/blob/29dcfd96fc686245b255523575e57165358fda58/docs/mkdocs.yml#L66

[dnth]

I have updated the PR following the suggestions above. Is there anything left out?

[FraPochetti]

I don't think so Dickson.
Thanks a lot once again!