Error in running Model Server Quickstart

[Mostafa-]

Hello Team,

I tried to follow the tutorial to implement the OpenVINO Model Server, but I got an error.

https://github.com/openvinotoolkit/model_server/blob/main/docs/ovms_quickstart.md

https://www.youtube.com/watch?v=AfytPrAVdfc

The error when running the inference service command line;

$ python3 face_detection.py --batch_size 1 --width 600 --height 400 --input_images_dir images --output_dir results

Request shape (1, 3, 400, 600)
Traceback (most recent call last):
File "face_detection.py", line 79, in <module>
result = stub.Predict(request, 10.0) # result includes a dictionary with all model outputs
File "/home/mostafa/.local/lib/python3.8/site-packages/grpc/_channel.py", line 690, in __call__
return _end_unary_response_blocking(state, call, False, None)
File "/home/mostafa/.local/lib/python3.8/site-packages/grpc/_channel.py", line 592, in _end_unary_response_blocking
raise _Rendezvous(state, None, None, deadline)
grpc._channel._Rendezvous: <_Rendezvous of RPC that terminated with:
status = StatusCode.NOT_FOUND
details = "Model with requested version is not found"
debug_error_string = "{"created":"@1638208144.932722687","description":"Error received from peer ipv6:[::1]:9000","file":"src/core/lib/surface/call.cc","file_line":1055,"grpc_message":"Model with requested version is not found","grpc_status":5}"

Seeking your support to fix it, please

BR,

Mostafa

[IntelSupport]

Hi Mostafa,

Thanks for reaching out.

We have verified the tutorial and we observe a similar issue as you when running the inference. We will further investigate this and get back to you with the information soon.

By the way, did you encounter any error at any steps in the tutorial before running Step 7 (Run Inference)?

Regards,

Aznie

[Mostafa-]

Hi Aznie,

Thanks for your reply.

No other error except that one.

[Mostafa-]

Hello Aznie,

Have you got the chance to check the issue, please?

Many Thanks,

Mostafa

[Wan_Intel]

Hi Mostafa-,

Thank you for reaching out to us.

For your information, we have validated the OpenVINO™ Model Server Quickstart. The results are shown as follow:

Based on your error message, the issue might be due to port or proxy. Please check the proxy setting and eliminate the proxy if possible.

On another note, you may refer to the following threads for more information related to your issue:

https://github.com/openvinotoolkit/model_server/issues/50

https://github.com/tensorflow/serving/issues/1770

Regards,

Wan

[Wan_Intel]

Hi Mostafa-,

Thank you for your question.

If you need any additional information from Intel, please submit a new question as this thread is no longer being monitored.

Regards,

Wan