Propagate collate_fn to InputTransform in ImageEmbedder

[krshrimali]

What does this PR do?

Looks like collate_fn was never propagated before. The reason it worked before: pretraining_transform was never called, hence the inputs were always tensors and not a list of tensors (so no need to collate).

Fixes #1218.

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 🙃

[codecov]

Codecov Report

Merging #1217 (9654ff9) into master (6da53fe) will increase coverage by 0.11%.
The diff coverage is 97.18%.

@@            Coverage Diff             @@
##           master    #1217      +/-   ##
==========================================
+ Coverage   91.06%   91.18%   +0.11%     
==========================================
  Files         286      286              
  Lines       12764    12790      +26     
==========================================
+ Hits        11623    11662      +39     
+ Misses       1141     1128      -13     

Flag	Coverage Δ
unittests	91.18% <97.18%> (+0.11%)	⬆️

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

Impacted Files	Coverage Δ
flash/image/embedding/vissl/transforms/__init__.py	100.00% <ø> (ø)
flash/core/adapter.py	97.14% <85.71%> (-1.27%)	⬇️
...lash/image/embedding/vissl/transforms/multicrop.py	98.11% <97.61%> (+1.14%)	⬆️
flash/core/data/io/input_transform.py	70.95% <100.00%> (ø)
flash/image/embedding/heads/vissl_heads.py	100.00% <100.00%> (ø)
flash/image/embedding/losses/vissl_losses.py	100.00% <100.00%> (ø)
flash/image/embedding/model.py	92.15% <100.00%> (+0.92%)	⬆️
...ash/image/embedding/transforms/vissl_transforms.py	100.00% <100.00%> (ø)
flash/image/embedding/vissl/hooks.py	98.21% <100.00%> (ø)
flash/text/question_answering/model.py	91.89% <0.00%> (-0.68%)	⬇️
... and 3 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 6da53fe...9654ff9. Read the comment docs.

[ethanwharris]

Awesome, LGTM 😃