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
But, in many cases, we do not create labels completely from scratch. Instead, we correct labels obtained using some method (sct_deepseg_sc, custom models, etc.). Thus, it would be a good idea to store the info about the method in the JSON sidacars, for example:
In the future, SCT functions will generate JSON sidecars tracking such info, see this PR: spinalcordtoolbox/spinalcordtoolbox#3394. Until then, and also for future models in development before integration to SCT, we could add an input arg to the manual_correction.py, allowing us to provide specific information to include in JSON sidecars.
The
manual_correction.py
currently generates the following JSON sidecars using code here:But, in many cases, we do not create labels completely from scratch. Instead, we correct labels obtained using some method (
sct_deepseg_sc
, custom models, etc.). Thus, it would be a good idea to store the info about the method in the JSON sidacars, for example:In the future, SCT functions will generate JSON sidecars tracking such info, see this PR: spinalcordtoolbox/spinalcordtoolbox#3394. Until then, and also for future models in development before integration to SCT, we could add an input arg to the
manual_correction.py
, allowing us to provide specific information to include in JSON sidecars.Relevant comments: #34, ivadomed/canproco#73
Our intranet convention: https://intranet.neuro.polymtl.ca/data/dataset-curation.html#json-sidecars
The text was updated successfully, but these errors were encountered: