GPU backend question

[jinz2014]

I have a question about running the example on an Intel integrated GPU. I got the following error when the backend_name is GPU. I am not clear which libraries or tools need to be installed. Must I install ngraph-onnx from the source ? I installed it using pip.

Thanks for your instruction.

File "test_onnx_model.py", line 41, in
runtime = ng.runtime(backend_name='GPU')
File "/home/cc/.local/lib/python3.6/site-packages/ngraph/runtime.py", line 35, in runtime
return Runtime(backend_name)
File "/home/cc/.local/lib/python3.6/site-packages/ngraph/runtime.py", line 43, in init
self.backend = Backend.create(backend_name)
RuntimeError: Unable to find backend 'GPU' as file '/home/cc/.local/lib/python3.6/site-packages/../../libgpu_backend.so'
Open error message '/home/cc/.local/lib/python3.6/site-packages/../../libgpu_backend.so: cannot open shared object file: No such file or directory'

[Michał Karzyński]

Hi there, we have a tutorial, which may be helpful located here: https://www.ngraph.ai/tutorials/onnx-tutorial

It looks like you would need to enable the Intel GPU backend in the “Before you build” section and then use INTELGPU instead of GPU when running the computation.