I am using intel openvino in windows. In that I am trying to run benchmark_app.exe with squeezenet1.1 as model and car image as test data in GPU. But I am getting the following error:
[Step 6/11] Configuring input of the model
[Step 7/11] Loading the model to the device
[ ERROR ] Error has occured for: pooling:pool1
Best_kernel.empty()(true) should be false
Cannot find a proper kernel with this arguments
And then I added the -c argument (i.e. the path to custom_kernels.xml). While running the sample with this setup, I am facing the following issue.
[Step 2/11] Loading Inference Engine
[ INFO ] GPU extensions is loaded "C:\Program Files (x86)\IntelSWTools\openvino_2020.2\deployment_tools\inference_engine\bin\intel64\Release"\cldnn_global_custom_kernels.xml
[ INFO ] InferenceEngine:
API version ............ 2.0
Build .................. 27579
Description ....... API
[ INFO ] Device info:
[ ERROR ] Failed to create plugin C:\Program Files (x86)\IntelSWTools\openvino_2020.2\deployment_tools\inference_engine\bin\intel64\Release\clDNNPlugin.dll for device GPU
Please, check your environment
Error loading custom layer configuration file: "C:\Program, File was not found at offset 0.
Please tell the solution to solve the above problems.
Have you selected the Inference engine Runtime for intel processor Graphics while installing OpenVINO?
If yes, Optionally you can follow the Additional installation steps for Intel Processor Graphics (GPU).
Please make sure about the system requirements.
First, please make sure that you are able to run the verification sample classification_sample_async.exe with default model and default image:
classification_sample_async.exe -i "C:\Program Files (x86)\IntelSWTools\openvino\deployment_tools\demo\car.png" -m "C:\Users<username>\Documents\Intel\OpenVINO\openvino_models\ir\public\squeezenet1.1\FP16\squeezenet1.1.xml" -d GPU
If your GPU device is supported and you followed steps to set up the environment variables and update GPU driver, then it should work.