Vishwesh

I can share the image offline, where it happens on my Ubuntu machine, but then again it's not necessary that it might happen at your end. I've shared the image...

To reproduce the issue use the below snippet: ``` import os from monai.transforms import ( LoadImage ) def main(): img_path = os.path.normpath('/put/image/path/here') load_img = LoadImage() img_d = load_img(img_path) print('Debug here')...

These are first being implemented in MONAI Core, before we start importing them for use.

This feature requires further discussion.

Moving it to backlog. As there is not sufficient time for all different kinds of AL strategies. This can be provided as an example later.

@ArjunNarayanan I want to add some highlights here that will be useful for you to formulate the solution. At the time of development of VitAutoEnc, we were looking to simply...

Yes you are on point @ArjunNarayanan , the UNETR architecture itself can be pre-trained (using both encoder and decoder of it, that way you should be able to modify token/patch-size...