erros using SWINUNETR

[ramdhan1989]

Hi, I got error when using SWINUNETR, my input size to the model is 4,1,96,96,96. When changing to 3DUXNET it works.

raise ValueError("Expected more than 1 spatial element when training, got input size {}".format(size)) ValueError: Expected more than 1 spatial element when training, got input size torch.Size([4, 768, 1, 1, 1])

please advise,

Thank you

[10dutel]

hello, i am using SWINUNETR too, but i can't properly run it yet.

RuntimeError: CUDA error: out of memory CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1.

same configuration, run 3d-uxnet is ok, but run SWINUNETR is error........Could you tell me how to handle this?

[10dutel]

ramdhan1989 hello@, i am using SWINUNETR too, but i can't properly run it yet.

RuntimeError: CUDA error: out of memory CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1.

same configuration, run 3d-uxnet is ok, but run SWINUNETR is error........Could you tell me how to handle this?

[BennettLandman]

I am closing the older bug reports as these were missed. We are now better tracking reports across the organization. Please re-open if this continues to be a blocker.