search

frankkramer-lab / covid19.MIScnn

Robust Chest CT Image Segmentation of COVID-19 Lung Infection based on limited data
GNU General Public License v3.0
88 stars 31 forks source link

Time #15

Open 10TREE-YEAR opened 3 years ago

10TREE-YEAR commented 3 years ago

Hello, I would like to ask you, what kind of running program do you use? I ran on the server and trained 5 times for 3 days. The speed is too slow, and you trained 1000 times, so can you tell me what you used to run the program method.

muellerdo commented 3 years ago

Hello @10TREE-YEAR,

can you specify what you mean with running program?

The script, which we used to generate the results of this paper, is located under scripts/run_miscnn.py As a GPU, we utilized a NVIDIA QUADRO RTX 6000.

Training time was less than 2 days per fold. If you didn't change anything in the hyperparameters of this script, then it's probably your hardware. I guess, either GPU or CPU bottleneck. Required RAM is less than 20GB and required GPU VRAM less than 17GB.

Cheers, Dominik