Fixed the unused train/val/test Mnist transforms

[lebrice]

When the 'transforms' arg of the [train|val|test]_dataloader method is None,
The MNISTDataModule would use self._default_transforms(), ignoring the value
of self.[train|val|test]_transforms.

I changed this to use instead either:

1. transform arg to xxxx_dataloader, if passed;
2. self.xxxx_transform, if set;
3. self._default_transforms().

Signed-off-by: Fabrice Normandin fabrice.normandin@gmail.com

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 to update the docs?
• Did you write any new necessary tests?

What does this PR do?

Fixes # (issue).

PR review

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-commenter]

Codecov Report

Merging #109 into master will decrease coverage by 0.00%.
The diff coverage is 100.00%.

@@            Coverage Diff             @@
##           master     #109      +/-   ##
==========================================
- Coverage   91.91%   91.90%   -0.01%     
==========================================
  Files          77       77              
  Lines        3944     3941       -3     
==========================================
- Hits         3625     3622       -3     
  Misses        319      319              

Flag	Coverage Δ
#unittests	91.90% <100.00%> (-0.01%)	⬇️

Impacted Files	Coverage Δ
pl_bolts/datamodules/mnist_datamodule.py	97.67% <100.00%> (-0.16%)	⬇️

---

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 024b574...e119cc4. Read the comment docs.