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

Supported target type is: multilabel-indicator. Got 'binary' instead. #18

Open
takfarine opened this issue Aug 10, 2022 · 1 comment
Open
Assignees
Labels
question Further information is requested

Comments

@takfarine
Copy link

takfarine commented Aug 10, 2022

No description provided.

@muellerdo
Copy link
Member

muellerdo commented Aug 10, 2022

Hello @takfarine,

have a look in the AUCMEDI docs for the CSV loader:
https://frankkramer-lab.github.io/aucmedi/reference/data_processing/io_interfaces/io_csv/#aucmedi.data_processing.io_interfaces.io_csv

In the following code snippet, you read the your csv data as one-hot-encoded:

ds = input_interface(interface="csv", path_imagedir=path_images,
                     path_data=path_csv, ohe=True, col_sample="filename",
                     ohe_range=cols)

This means that your csv have to look something like the right side here from google images:
image

However, your data look like the left side, which is why you need to set one hot encoding ohe to False, add the col_class parameter to your column label and remove the ohe_range parameter.

Then it should work! :)

Cheers,
Dominik

@muellerdo muellerdo added the question Further information is requested label Aug 12, 2022
@muellerdo muellerdo self-assigned this Aug 12, 2022
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