(Resolved)Libtorch1.5_cu92 win7: torch.cat RuntimeError: error in LoadLibraryA

Win7 64bit

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.

I will try it. thanks

Fixed, thank you very much.