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

Improved Tensor Dimension Handling in predict_masks Method for fine tuning #580

Open
wants to merge 2 commits into
base: main
Choose a base branch
from

Conversation

sushmanthreddy
Copy link

@sushmanthreddy sushmanthreddy commented Sep 29, 2023

close #581

  1. Introduction of Conditional Check:

    • In the enhanced predict_masks method, a conditional check is introduced to ascertain whether the image_embeddings tensor's batch size aligns with that of tokens.
    • The check (if image_embeddings.shape[0] != tokens.shape[0]:) is crucial as it guides the subsequent operation: torch.repeat_interleave.
  2. Usage of torch.repeat_interleave:

    • The function torch.repeat_interleave is utilized to expand the image_embeddings tensor along the batch dimension to match the batch size of tokens, ensuring consistency in tensor dimensions as the method progresses.
    • In the original implementation, torch.repeat_interleave is applied directly, potentially leading to misalignments in tensor dimensions if the batch sizes are already aligned.
  3. Ensuring Consistency:

    • The conditional check ensures that torch.repeat_interleave is applied only when necessary, preventing potential dimension misalignment and ensuring consistent tensor handling within the predict_masks method.

@facebook-github-bot
Copy link

Hi @sushmanthreddy!

Thank you for your pull request and welcome to our community.

Action Required

In order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you.

Process

In order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA.

Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with CLA signed. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.

If you have received this in error or have any questions, please contact us at [email protected]. Thanks!

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Sep 29, 2023
@sushmanthreddy
Copy link
Author

sushmanthreddy commented Sep 29, 2023

@HannaMao can u pls review this pull request?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Improved Tensor Dimension Handling in predict_masks Method
2 participants