RuntimeError: cuda runtime error (2) : out of memory

[hzc12]

Hi I face some problems when I run this project.

.......... Networks tnittaltzed .......... ==> Loading checkpoint ' . checkpoints/101. DAVS checkpoint . pth. tar ' ==>Loaded checkpoint ' . /checkpoints/101 DAVS checkpotnt , pth,tar'. (step 21145000) THCudaCheck FAIL file=/opt/conda/conda-bld/pytorch_ 1511304568725/work/torch/lib/THC/generic/THCStorage.cu line=66 error=2 : out of memory Trackback (most recent call last): File "test_all.py"，line 43, in module.test_train() File "/home/downloads/gp/Talkingface/Test_Gen_Models/Test_Video_Model.py", line 88, in test_train self.optimizer_G_test.step() File "/home/anaconda2/lib/python2.7/site-packages/torch/optim/adam.py', line 68, in step denom = exp_avg_sq.sqrt().add_(group['eps'])

RuntimeError: cuda runtime error (2) :out of memory at /opt/conda/conda-bld/pytorch_ 1511304568725/work/torch/lib/THC/generic/THCStorage.cu:66

Can you tell me the version of your graphics card and the version of cuda & cudnn? thank you very much.

[Hangz-nju-cuhk]

Hi, I used one Titan Black GPU with 6GB memory for testing, so it is unlikely that it would run out of memory. I am really curious. I used both cuda 8.0 and 9.0 before and they all worked fine.

[cpmss521]

have any progress? i have same problems,

[Vensss]

Hi, I have exactly the same problem, I used one GTX1050 with 4GB memory.

[Vensss]

The problem is solved! I used the pytorch0.4.0 and cudnn 7.1.3