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

Matches and Config: #74

Open
mouaazranjha opened this issue Aug 28, 2024 · 2 comments
Open

Matches and Config: #74

mouaazranjha opened this issue Aug 28, 2024 · 2 comments

Comments

@mouaazranjha
Copy link

Hi, thanks for this great repo. I was wondring from where i can change max number of features and matches that model will detect and try to match, similarly where is the threshold value for detected feature and match.
As i was testing i refered to "matches" from:

matches, certainty = roma_model.sample(warp, certainty)

As correct matches but if two images are totally different i.e i can manually verify there is not a single match in between them, len(matches) is still 10000.

What i want to acheive is only true matches even though they are less in number.

Any plan to launch onnx/TRT model in future?

@Parskatt
Copy link
Owner

Parskatt commented Nov 1, 2024

  1. I would look at the average certainty of the warp before sampling as indicating the overlap, rather than after sampling.
  2. You can set the number of samples in roma_model.sample(warp, certainty, num=5_000)

@Parskatt
Copy link
Owner

Parskatt commented Nov 1, 2024

Regarding ONNX, no plans from my end currently.

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