-
Notifications
You must be signed in to change notification settings - Fork 74
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
About Python API #36
Comments
Just wondering, in case if we want to use our own samples, do you suggest to look into parameters to tune further to improve accuracy? |
I suggest starting with the algorithm's default parameters and evaluating their accuracy with your samples. If the results are not up to par, it might be more beneficial to consider a different algorithm. Fine-tuning the parameters should be your last resort, as it can be a complex and time-consuming process. |
I understand, I am yet to read through each approach details and understand a bit more meanwhile do you have any recommendation on the approach/method that would be generizable to any data? I have quick glance and looks like GIM is testing with youtube images. |
Update: I added a Python API using FastAPI. See the details in this PR: #77. I included a server and an example client. You can start the API with the following commands: python -m imcui.api.server Then, open another terminal: python -m imcui.api.client |
Thanks for providing this brilliant repo.
It works well on the web app. May I know is there a Python API I can use in the Python script? For example, I have two images and want to perform keypoint detection, matching, and ransac with different methods.
Thank you so much!
The text was updated successfully, but these errors were encountered: