doc: using collate_fn

[AlanBlanchet]

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.

Motivation

collate_fn isn't set by default. We need to use pytorch's default collator.

Modification

Just the doc

BC-breaking (Optional)

Does the modification introduce changes that break the backward-compatibility of the downstream repos?
If so, please describe how it breaks the compatibility and how the downstream projects should modify their code to keep compatibility with this PR.

Use cases (Optional)

If this PR introduces a new feature, it is better to list some use cases here, and update the documentation.

Checklist

1. Pre-commit or other linting tools are used to fix the potential lint issues.
2. The modification is covered by complete unit tests. If not, please add more unit test to ensure the correctness.
3. If the modification has potential influence on downstream projects, this PR should be tested with downstream projects, like MMDet or MMPreTrain.
4. The documentation has been modified accordingly, like docstring or example tutorials.

[AlanBlanchet]

Would solve :

• An error occurred while adding AugFPN, TypeError: conv2d() received an invalid combination of arguments - got (tuple, Parameter, Parameter, tuple, tuple, tuple, int) #10923
• Problem in migrating InternImage into mmdetection 3 #11039

And maybe :

• Train with multiple(4) GPUs #10496