cuda error: out of memory
YZHUA opened this issue · comments
I get in trouble when trying to train the suggested RGBD dataset using GTX1080Ti.
RuntimeError: cuda runtime error (2) : out of memory at /opt/conda/conda-bld/pytorch_1524586445097/work/aten/src/THC/generic/THCStorage.cu:58.
I have tried the python 3.6.4 with torch 1.0.1, 0.4.0, 0.4.1, none of them works. All of them is ok for testing. The weired thing is that both 0.4.0 and 0.4.1 achieve about 0.5s per image, while 1.0.1 version achieve 4s per image. Anyway, should I try modify some parameters of commmend line to make it work for training on GTX1080Ti?
There might be two possible way you can try
(1) Reduce the batch sie
(2) If you download my code implemented by 0.3.0 version,
you'd better put <with torch.no_grad():> before the psnet() line.
or you can download from different branch.