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.

Sign up for GitHub

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

Jump to bottom

Can't train a model with only 4 images #38

Open
thibaultdvx opened this issue Mar 25, 2024 · 3 comments · May be fixed by #42
Open

Can't train a model with only 4 images #38

thibaultdvx opened this issue Mar 25, 2024 · 3 comments · May be fixed by #42

Comments

@thibaultdvx
Copy link
Collaborator

clinicadl_handbook/src/training_classification.py

Line 316 in caab842

!clinicadl train classification data_oasis/CAPS_example slice_classification_t1 data_oasis/split/4_fold/ data_oasis/maps_classification_2D_slice_resnet18 --n_splits 4 --architecture resnet18

There are only 4 images in the OASIS example dataset. It is not enough to train a model, as test and validation tests must contain at least 2 images (1 AD and 1 CN).
@thibaultdvx thibaultdvx changed the title Can't train a model with only four image Can't train a model with only 4 images Mar 25, 2024
@thibaultdvx
Copy link
Collaborator Author

@NicolasGensollen I would like to add a file with more data (10 images, just enough to train a model) on the server. How can I do that?

@NicolasGensollen
Copy link
Member

@thibaultdvx You need administrative rights on the machine to do that.
I think the easiest way would be that you put them on the Lustre such that I can get them and upload them.
WDYT ?

@thibaultdvx
Copy link
Collaborator Author

@NicolasGensollen sounds good to me. I'll let you know when it is done.

@thibaultdvx thibaultdvx linked a pull request Mar 26, 2024 that will close this issue
Draft
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

38 add data to train model thibaultdvx/clinicadl_handbook
2 participants
@NicolasGensollen @thibaultdvx