Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update simmim_neck.py #1875

Open
wants to merge 3 commits into
base: main
Choose a base branch
from

Conversation

ashutoshsingh0223
Copy link

@ashutoshsingh0223 ashutoshsingh0223 commented Feb 25, 2024

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.

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.
@CLAassistant
Copy link

CLAassistant commented Feb 25, 2024

CLA assistant check
All committers have signed the CLA.

@ashutoshsingh0223
Copy link
Author

Could a maintainer please review this?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants