Mgithus

Results 4 comments of Mgithus

While fine tuning the Swin UNETR, Training loss is not decreasing and training gets crashed after 10 epohs

Cuda out of memory ... Crashing of training problem was solved by reducing no.of workers and batch size to 1... But problem with increasing loss after 5th or 6th epoch...

While fine tuning the Swin UNETR, Training loss is not decreasing and training gets crashed after 10 epohs

My pleasure... I will try it .... Thnx....

While fine tuning the Swin UNETR, Training loss is not decreasing and training gets crashed after 10 epohs

I used Google Colab Pro Plus and it automatically installed the latest versions of Monai and Pytorch directly without specifying a specific version. However, when I tried to run this...

RuntimeError: CUDA out of memory

I tried to but didn't work. So went for google colab.