# Why is it actually impossible to load onnxruntime.dll?

1

Using the tutorial from the developers at Microsoft, I followed the tutorial created at https://docs.microsoft.com/en-us/dotnet/machine-learning/tutorials/object-detection-onnx.

I made sure to install CUDA V10.1.243 and cuDNN 7.6.5 from Nvidia's site.

Yet somehow, even after copying the entire contents of C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.1\bin to my project binary's directory at machinelearning-samples\samples\csharp\end-to-end-apps\ObjectDetection-Onnx\OnnxObjectDetectionApp\bin\Debug\netcoreapp3.0, I keep running into the following error while compiling the example program MS provided: Exception thrown: 'System.DllNotFoundException' in System.Private.CoreLib.dll An exception of type 'System.DllNotFoundException' occurred in System.Private.CoreLib.dll but was not handled in user code Unable to load DLL 'onnxruntime' or one of its dependencies: The specified module could not be found. (0x8007007E).

This should make sure they are accessible from the PATH right? I'm also including their original location in NVIDIA GPU Toolkit in the system PATH as well. I am using the latest version of Visual Studio 2019 to load and compile this solution. Is there anyone out there that has been able to run this code successfully, and if so, how?

c#
visual-studio
machine-learning
ml.net
ml.net-model-builder
asked on Stack Overflow Aug 25, 2020 by lolsky • edited Aug 28, 2020 by lolsky