Hi,
My gcc and Ubuntu versions match exactly those in README.md, but I have CUDA 10.1. I set up the environment exactly as in README.md.
When trying to run the code, I find CUDA 10.1 causing trouble:
if cudatoolkit is not 9.0 -> ImportError: libcudart.so.9.0: cannot open shared object file: No such file or directory
if cudatoolkit is 9.0 -> ImportError:.../VL-BERT/refcoco/../common/lib/roi_pooling/C_ROIPooling.cpython-36m-x86_64-linux-gnu.so: undefined symbol: __cudaRegisterFatBinaryEnd
Is there any fix other than having to install CUDA 9.0?
Hi, My gcc and Ubuntu versions match exactly those in README.md, but I have CUDA 10.1. I set up the environment exactly as in README.md. When trying to run the code, I find CUDA 10.1 causing trouble:
Is there any fix other than having to install CUDA 9.0?