You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I think this would help this library be even more useful than it already is for the currently ongoing kaggle competition associated with this class.
Pitch
I think this is a relatively small change and I would like to make it. I am opening this issue to solicit comments. If there is no major opposition I'll open a PR for this later this evening after reading the contributing instructions.
Alternatives
None
Additional context
None
The text was updated successfully, but these errors were encountered:
Hi, @dankleeman. I was planning to implement this but then noticed that there are only three test subjects. That's why the split_namevariable exists. Feel free to open a PR if you think it's worth it.
there are three subjects, but those are for testing your pipeline. This way real dataset won't be visible to contestants but will be visible to your kaggle notebook, please add it. So it will be super useful in making submissions.
🚀 Feature
The RSNA Spine Fracture class is hard-coded to only load the training images: https://github.com/fepegar/torchio/blob/main/src/torchio/datasets/rsna_spine_fracture.py#L71
I propose implementing an argument at initialization to allow this class to ingest test images as well. I see this available in another similar class here: https://github.com/fepegar/torchio/blob/main/src/torchio/datasets/rsna_miccai.py#L61
Motivation
I think this would help this library be even more useful than it already is for the currently ongoing kaggle competition associated with this class.
Pitch
I think this is a relatively small change and I would like to make it. I am opening this issue to solicit comments. If there is no major opposition I'll open a PR for this later this evening after reading the contributing instructions.
Alternatives
None
Additional context
None
The text was updated successfully, but these errors were encountered: