microsoft / Recursive-Cascaded-Networks

[ICCV 2019] Recursive Cascaded Networks for Unsupervised Medical Image Registration
https://arxiv.org/abs/1907.12353
MIT License
361 stars 87 forks source link

LPBA segmentation ground truth #31

Closed MingR-Ma closed 4 years ago

MingR-Ma commented 4 years ago

Thanks for your work. I'm using your dataset to train my model , I want to use LPBA to evaluate my model , but I can't find where the LPBA ground truth is. Would you provide the LPBA ground truth?

zsyzzsoft commented 4 years ago

We have instructions on how to evaluate on LPBA (see README):

Similarly, to evaluate the pretrained 10-cascade VTN (for brain) on the LPBA dataset: python eval.py -c weights/VTN-10-brain -g YOUR_GPU_DEVICES

Replace "weights/VTN-10-brain" by the path of your own checkpoint to evaluate it.