Win7 64bit
CUDA9.2
Libtorch1.5+cu92
when I use “module.forward(inputs).toTensor()”, crashed.
I print out the exception, something like it below:
"
input = torch.cat([argument_2, x1], 1)
~~~~~~~~~ <— HERE
return (_17).forward(input, )
…
…
…
RuntimeError: error in LoadLibraryA
"
But I can run cpu traced model well.
This error should be fixed in PyTorch 1.5.0
, if I’m not mistaken.
If you are using an older version, you could update or use this workaround.
Someone else found out that it could also be caused by the antivirus. See https://blog.csdn.net/weixin_38314865/article/details/103840899.
I double checked that, I use libtorch1.5, and I use pytorch 1.5.0 to trace and saved my model.
Today I downloaded the latest nightly build libtorch version, has the same issue.
I tried it, not work for me. Pytorch is OK, no issue, Libtorch has this situation.
For libtorch, just copy all the DLLs to the location of your executable.
Fixed, thank you very much.