search

StefanDenn3r / Spatio-temporal-MS-Lesion-Segmentation

Code for the paper 'Spatio-temporal Learning from Longitudinal Data for Multiple Sclerosis Lesion Segmentation'
MIT License
17 stars 3 forks source link

Issue with the number of files created by the method #1

Open arthursw opened 4 years ago

arthursw commented 4 years ago

Hi,

I am currently working on a comparison of MS lesion segmentation methods as described in this post.

I started training this method (Spatio-temporal-MS-Lesion-Segmentation), but I noticed it generates a large amount of files for each patient (in the patientName/data/ directory). It generated 6260 files for one patient, meaning it could generate up to 250 000 files to process my database. The problem is that the number of file I can create on the computing grid I use (Jean Zay) is limited (I can only create 500k files and I already use a big amount of this quota).

So I am wondering if there is a simple way to store this data in an archive instead?

Thanks! Arthur