Refactor ImageClassification backbones

[ananyahjha93]

What does this PR do?

1. Breaks the backbones.py file into parts for easier maintainability.
2. Adds wide resnet weights from vissl.
3. Updates resnet architecture to accommodate wide resnet weights and customizations for ssl resnet based training.
4. In process, the PR removes the requirement of torchvision for the resnet backbones.

Before submitting

• Was this discussed/approved via a Github issue? (no need for typos and docs improvements)
• Did you read the contributor guideline, Pull Request section?
• Did you make sure your PR does only one thing, instead of bundling different changes together?
• Did you make sure to update the documentation with your changes?
• Did you write any new necessary tests? [not needed for typos/docs]
• Did you verify new and existing tests pass locally with your changes?
• If you made a notable change (that affects users), did you update the CHANGELOG?

PR review

• Is this pull request ready for review? (if not, please submit in draft mode)

Anyone in the community is free to review the PR once the tests have passed.
If we didn't discuss your PR in Github issues there's a high chance it will not be merged.

Did you have fun?

Make sure you had fun coding 🙃

[pep8speaks]

Hello @ananyahjha93! Thanks for updating this PR.

There are currently no PEP 8 issues detected in this Pull Request. Cheers! 🍻

Comment last updated at 2021-07-30 16:53:58 UTC

[codecov]

Codecov Report

Merging #626 (1bc6889) into master (22cd201) will decrease coverage by 0.08%.
The diff coverage is 88.88%.

@@            Coverage Diff             @@
##           master     #626      +/-   ##
==========================================
- Coverage   89.96%   89.87%   -0.09%     
==========================================
  Files         149      155       +6     
  Lines        8458     8654     +196     
==========================================
+ Hits         7609     7778     +169     
- Misses        849      876      +27     

Flag	Coverage Δ
unittests	89.87% <88.88%> (-0.09%)	⬇️

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

Impacted Files	Coverage Δ
...ash/image/classification/backbones/transformers.py	60.00% <60.00%> (ø)
...lash/image/classification/backbones/torchvision.py	80.95% <80.95%> (ø)
flash/image/classification/backbones/resnet.py	90.85% <90.85%> (ø)
flash/core/utilities/url_error.py	100.00% <100.00%> (ø)
flash/image/__init__.py	100.00% <100.00%> (ø)
flash/image/backbones.py	100.00% <100.00%> (+13.72%)	⬆️
flash/image/classification/backbones/__init__.py	100.00% <100.00%> (ø)
flash/image/classification/backbones/timm.py	100.00% <100.00%> (ø)
flash/image/classification/model.py	76.92% <100.00%> (-1.93%)	⬇️
flash/image/embedding/model.py	68.42% <100.00%> (-14.04%)	⬇️
... and 8 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 22cd201...1bc6889. Read the comment docs.

[ethanwharris]

LGTM, one small issue

[ethanwharris]

Awesome, LGTM 😃