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

SAM Clip confidence level? #72

Closed
1 task done
shersoni610 opened this issue Oct 31, 2023 · 2 comments
Closed
1 task done

SAM Clip confidence level? #72

shersoni610 opened this issue Oct 31, 2023 · 2 comments
Labels
question Further information is requested

Comments

@shersoni610
Copy link

Search before asking

  • I have searched the Autodistill issues and found no similar feature requests.

Question

Hello,

I was wondering if the following line is correct in the code:

def predict(self, input: str, confidence: int = 0.5) -> sv.Detections:

Shouldn't this value be float instead of int?

Thanks

Additional

No response

@shersoni610 shersoni610 added the question Further information is requested label Oct 31, 2023
@capjamesg
Copy link
Member

@artyaltanzaya Should the confidence value be an integer? I think CLIP returns raw values from 0-1 that we don't post-process, looking at the code in our implementation.

@capjamesg
Copy link
Member

@shersoni610 We have replaced the autodistill-sam-clip module with the new model combination API. See the autodistill-sam-clip README for instructions on how to use the new module.

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

No branches or pull requests

2 participants