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

Apply pre-trained model on a single subject #55

Open
giuseppeantoniomotisi opened this issue Jan 20, 2025 · 1 comment
Open

Apply pre-trained model on a single subject #55

giuseppeantoniomotisi opened this issue Jan 20, 2025 · 1 comment
Labels
question Further information is requested

Comments

@giuseppeantoniomotisi
Copy link

Hello everyone I am currently facing this issue regarding pre-trained harmonized model.
After fit model on my training set (949 subjects x 587 features) on AGE and FIQ covariates, I saved the model and the load as shown in the documentation. Then, I tried to apply the model on a single subject (1x587 features) using 'applyModelOne' but I got ValueError('Argument data contains more than one sample!'). I have the same and the same number of covariates used for training.

Can someone please help me?

@rpomponio rpomponio added the question Further information is requested label Jan 21, 2025
@rpomponio
Copy link
Owner

rpomponio commented Jan 21, 2025

I'm not sure where you found that function, can you point to the place in the documentation?

It's possible that function is for internal use, and not intended as an end-user utility.

You should be able to apply a pre-trained harmonization model on a dataset of one subject, so long as the latter is a two-dimensional object (which it seems to be) and the subject is from one of the sites in your training data.

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