解决ONNX无法找到CUDA路径问题的方法
报错
RuntimeError: D:\a\_work\1\s\onnxruntime\python\onnxruntime_pybind_state.cc:857 onnxruntime::python::CreateExecutionProviderInstance CUDA_PATH is set bu
t CUDA wasnt able to be loaded. Please install the correct version of CUDA andcuDNN as mentioned in the GPU requirements page (https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#requirements), make sure they're in the PATH, and that your GPU is supported.
问题分析
onnx找到了gpu,但是还是不能调用
解决办法
-
先检查一下cudnn的环境变量配置是否正确,如果不正确,先看看怎么安装cudnn
-
接下来是环境变量没问题的情况
环境变量没问题的话,一般就是cudnn和cuda以及onnx的版本不匹配
版本匹配看这里
查看好自己cudnn和cuda对应onnx版本后,输入这个
pip install onnxruntime-gpu==what_you_want_version --extra-index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/onnxruntime-cuda-12/pypi/simple/
将what_you_want_version
换成你需要的版本,如我是cuda12.x以及cudnn8.x
那么就是
pip install onnxruntime-gpu==1.18.1 –extra-index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/onnxruntime-cuda-12/pypi/simple/
作者:烟花节