Separate SC seg and lesion seg predictions into 2 separate files after inference - Githubissues

ivadomed / model_seg_sci

Deep-learning based segmentation of the spinal cord and intramedually lesions in traumatic and non-traumatic SCI

MIT License

12 stars 2 forks source link

Separate SC seg and lesion seg predictions into 2 separate files after inference #51

Closed naga-karthik closed 1 year ago

naga-karthik commented 1 year ago

Since we're training region-based models that obtain SC segmentation and lesion segmentation together, the inference also results in a single file containing both the predictions with sc-seg = 1 and lesion-seg = 2. It would be more useful to separate them into two separate files so that the user can obtain whatever type of prediction they want.

TODO:

[x] Add an argument in run_inference.py that asks for the type of segmentation (sc or lesion) and only generates the outputs for either of them or both

naga-karthik commented 1 year ago

This feature has been implemented in commit https://github.com/ivadomed/model_seg_sci/pull/40/commits/4344b758a757ba307c021c25ec7a97d126a41756