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

📖 Model Config Options Documentation #2

Open
abegehr opened this issue Aug 20, 2024 · 1 comment
Open

📖 Model Config Options Documentation #2

abegehr opened this issue Aug 20, 2024 · 1 comment

Comments

@abegehr
Copy link

abegehr commented Aug 20, 2024

In the readme it states we should configure the model with parameters threshold, overlap, and maxObjects:

model?.configure(threshold: threshold, overlap: overlap, maxObjects: maxObjects)

However it's not documented what these parameters do and what acceptable values are.

I found the defaults here
Based on that, I'd assume:

  • threshold: definition of confidence from here (0..1)
  • overlap: definition of overlap from here (0..1)
  • maxObjects: the maximum number of objects inferred at a time (≥1)

are those correct assumptions?

@nailsonlinux
Copy link

@abegehr I've checked the code for you, the overlap is what is meant to be, you set the IoU threshold as you can check it here:

thresholdProvider.values = ["iouThreshold": MLFeatureValue(double: self.overlap),

and for better understanding of this, you can check 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

No branches or pull requests

2 participants