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

Set image dim=2 for the computation of image embeddings #778

Closed
wants to merge 1 commit into from

Conversation

caroteu
Copy link
Contributor

@caroteu caroteu commented Nov 13, 2024

@anwai98 The image dimension needs to be passed here, else datasets with (1,width,height) type images will cause an error.

@anwai98
Copy link
Contributor

anwai98 commented Nov 13, 2024

Hi @caroteu,
We shouldn't fix the number of dimensions in the class method itself.
Also, if we have monochannel inputs, we should use the inputs as (H x W) (which is the expectation in micro-sam)

@anwai98 anwai98 closed this Nov 13, 2024
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