Open wsh2836741 opened 6 years ago
Do you use cudnn? It should not suffer "out of memory" when the largest scale is 1600*1600 with a titan xp.
thx,i have solved the problem by using cudnn,and 8G is enough.
hello,when I run demo.py.It has the following errors: F0510 10:28:22.312146 15884 syncedmem.cpp:56] Check failed: error == cudaSuccess (2 vs. 0) out of memory what should i do?I have changed the scales,like this: scales=((300,300),(700,700),(700,500),(700,300),(1100,1100))
Do you use cudnn? It should not suffer "out of memory" when the largest scale is 1600*1600 with a titan xp.
Thank you. USE_CUDNN := 1
solved the issue.
Thanks for excellent work.But i am confused,it said 'out of memory' when i use titan xp GPU(12G).And the largest scale i can use is 1100*1100.Thank you in advice.