Update simmim_neck.py

[ashutoshsingh0223]

Motivation

Enhancement to SimMIM module to enable usage in non-RGB cases.

Modification

Update SimMIMLinearDecoder with target_channels. The downstream loss for SimMIM i.e. the PixelReconstructionLoss already allows user to set the number of channels through the channel argument. Useful in cases when reconstructing non-rgb images.
The value to target_channels is hardcoded to 3 to ensure all existing checkpoints work.

Use cases (Optional)

SimMIM can now be trained for grayscale or hyperspectral images.

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

Checklist

Before PR:

• Pre-commit or other linting tools are used to fix the potential lint issues.
• Bug fixes are fully covered by unit tests, the case that causes the bug should be added in the unit tests.
• The modification is covered by complete unit tests. If not, please add more unit test to ensure the correctness.
• The documentation has been modified accordingly, like docstring or example tutorials.

After PR:

• If the modification has potential influence on downstream or other related projects, this PR should be tested with those projects, like MMDet or MMSeg.
• CLA has been signed and all committers have signed the CLA in this PR.

[CLAassistant]

All committers have signed the CLA.

[ashutoshsingh0223]

Could a maintainer please review this?