Getting cuda error while running

Part 1 (2018) Beginner (2018)
1

Hi,
I am getting this cuda error when I run the Char3model from the deep learning course lesson 6(RNN’s):

This is the code that i am trying to run:-
m = Char3Model(vocab_size, n_fac).cuda()

And this is the error:-
RuntimeError: cuda runtime error (59) : device-side assert triggered at /opt/conda/conda-bld/pytorch_1535491974311/work/aten/src/THC/generic/THCTensorCopy.cpp:20

2

Hi Jordan, did you figure this out? I’m running into the same issue

3

Hi,
Yeah, I did figure this out. I just added .cpu() instead of .cuda(). But, even if you leave it as it is, Pytorch automatically detects if you’re running it on a gpu or a cpu. Sorry for the late reply.