Question on DentalSegmentor memory error

Support
1

Hello,

I’ve selected cuda from the following device option in DentalSegmentor:
image

When I click on Apply button, I get the following error:

####################################################################### Please cite the following paper when using nnU-Net: Isensee, F., Jaeger, P. F., Kohl, S. A., Petersen, J., & Maier-Hein, K. H. (2021). nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nature methods, 18(2), 203-211. ####################################################################### There are 1 cases in the source folder I am process 0 out of 1 (max process ID is 0, we start counting with 0!) There are 1 cases that I would like to predict Predicting volume: perform_everything_on_device: True Prediction on device was unsuccessful, probably due to a lack of memory. Moving results arrays to CPU

RAM size: 16 GB
GPU: NVidia Geforce GTX

Please help, Thank you.

2

@lassoan @pieper @cpinter @muratmaga

Could you help me solve this issue?

3

You can try to crop and downsample your input image (using Crop volume module) to reduce memory need or try with a GPU with more memory.

You may also find more information in the application log.

1 Like