perp
Results
3
comments of
perp
I reduce both limit from 30 to 10 , but still cuda out of memory on ti2080 12G
1. You need write a python script which walk through you image folder and get the filename and write to an train or val.lst 2. you need https://github.com/mcordts/cityscapesScripts to convert...
@BryantLJ You must enbale OpenBLAS multi threaded. The time cost should be 1/3 of your current time cost.