[CLDNN ERROR]. clGetPlatformIDs error -1001

[huang06]

Environment:

• OS: Ubuntu 20.04.1 LTS
• CPU: i5-1145GRE
• GPU: Intel® Iris® Xe Graphics
• OpenVINO: 2021.1.110
• Python: 3.8.5

Problem:

I encountered the error message while running the sample code with GPU plugin:

python_script="/opt/intel/openvino_2021/deployment_tools/tools/benchmark_tool/benchmark_app.py"
demo_image="/opt/intel/openvino_2021/deployment_tools/demo/car.png"
python3 $python_script \
        -m googlenet-v1.xml \
        -d GPU \
        -api async \
        -i $demo_image \
        -progress true

[Step 1/11] Parsing and validating input arguments
[ WARNING ]  -nstreams default value is determined automatically for a device. Although the automatic selection usually provides a reasonable performance, but it still may be non-optimal for some cases, for more information look at README.
[Step 2/11] Loading Inference Engine
[ INFO ] InferenceEngine:
         API version............. 2.1.2021.1.0-1237-bece22ac675-releases/2021/1
[ ERROR ] Failed to create plugin /opt/intel/openvino_2021/deployment_tools/inference_engine/lib/intel64/libclDNNPlugin.so for device GPU
Please, check your environment
[CLDNN ERROR]. clGetPlatformIDs error -1001
Traceback (most recent call last):
  File "/opt/intel/openvino_2021/python/python3.8/openvino/tools/benchmark/main.py", line 77, in run
    version = benchmark.get_version_info()
  File "/opt/intel/openvino_2021/python/python3.8/openvino/tools/benchmark/benchmark.py", line 51, in get_version_info
    for device, version in self.ie.get_versions(self.device).items():
  File "ie_api.pyx", line 236, in openvino.inference_engine.ie_api.IECore.get_versions
RuntimeError: Failed to create plugin /opt/intel/openvino_2021/deployment_tools/inference_engine/lib/intel64/libclDNNPlugin.so for device GPU
Please, check your environment
[CLDNN ERROR]. clGetPlatformIDs error -1001

 I followed the two instructions to install extra packages:

1. https://docs.openvinotoolkit.org/latest/openvino_docs_install_guides_installing_openvino_linux.html#additional-GPU-steps
2. https://www.intel.com/content/www/us/en/support/articles/000057923/software/development-software.html

But I still got the same error message.

[Iffa_Intel · Accepted solution]

Greetings,

First and foremost, please take a note that only these Operating Systems are currently supported:

• Ubuntu 18.04.x long-term support (LTS), 64-bit
• CentOS 7.6, 64-bit (for target only)
• Yocto Project v3.0, 64-bit (for target only and requires modifications)

Other OS than these is expected to encounter errors as they are not validated.

Besides, make sure that you had initialized setupvars.sh each time you open a new terminal. Initialization message should appear once you invoke the script or it will automatically appear if you set it up permanently.

For Python version, in my experience as a user, I suggest you use either 3.7 or 3.6.

Sincerely,

Iffa

[Iffa_Intel]

Greetings,

Intel will no longer monitor this thread since we have provided a solution. If you need any additional information from Intel, please submit a new question

Sicerely,

Iffa