Naga Karthik Enamundram

@alexander-soare I was wondering whether if it makes too much of a difference in the results? Have you tried comparing the two?

well well! glad that I found this issue sooner than later, thanks @valosekj for linking it! my ideas were related to dcm lesion segmentation, for which, I was planning on...

Hello, I am wondering what's the status of this issue? Are 3D NMS and 3D ROI Align going to be implemented in future version of torchvision anytime soon? As the...

I could solve this issue by installing triton separately (i.e. by doing `pip install triton`)

> so that the contrast-agnostic model can more easily be reproduced, no? Yes! We required the disc labels for vertebral labeling and the C2-C3 CSA computation via `sct_process_segmentation`. Hence, adding...

Weirdly, despite this error, I was able to login to one of the 4 mila nodes ``` naga-karthik.enamundram@login-3:~$ pwd /home/mila/n/naga-karthik.enamundram ``` I think `mila init` ran properly as I could...

With PR https://github.com/spinalcordtoolbox/spinalcordtoolbox/pull/4783, as we're moving away from the monai-based model for `seg_sc_contrast_agnostic`, I believe this issue is not relevant anymore? (i.e. we don't have to explicitly set `num_workers` on...

Hi @AntoineGuenette, thanks for the opening the issue. Since you have a M-series MacBook, I have a workaround that enables using MPS (apple's GPU) to run the inference. Here are...

Hey @AntoineGuenette, I think the script is not finding the model. Can you update the path to the model and try again? ``` -path-model /Users/antoineguenette/spinalcordtoolbox/data/deepseg_models/model_seg_sc_contrast_agnostic_nnunet/nnUNetTrainer__nnUNetPlans__3d_fullres/ ```

That's strange! Could you post the output of `pip list`? I don't get this error and i'm wondering if there's any package version mismatch