OpenVINO serving - Servable not found for request

Question

I am trying to serve a OpenVINO model using procedure mentioned in OpenVINO model server repo but encountering the below issue when trying to get the metadata for the model.
Command I am executing is

python get_serving_meta.py --grpc_address 0.0.0.0 --grpc_port 9001 \  
--model_name my_model --model_version 1

Error I am receiving is:

    Getting model metadata for model: my_model  
    Traceback (most recent call last):
      File "get_serving_meta.py", line 97, in <module>  
    result = stub.GetModelMetadata(request, 10.0) # result includes a dictionary with all model outputs


    File "/root/.pyenv/versions/3.6.8/lib/python3.6/site-packages/grpc/_channel.py", line 549, in __call__  
    return _end_unary_response_blocking(state, call, False, None) 
File "/root/.pyenv/versions/3.6.8/lib/python3.6/site-packages/grpc/_channel.py", line 466, 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 = "Servable not found for request:Specific(my_model, 1)"  
        debug_error_string = "{"created":"@1555239621.319103888","description":"Error received from peer","file":"src/core/lib/surface/call.cc","file_line":1039,"grpc_message":"Servable not found for request: Specific(my_model, 1)","grpc_status":5}"

To get the docker container up, cmd I am using is:

docker run --rm -d -v /home/rachit/models/:/opt/ml:ro -p 9001:9001  \
docker.io/intelaipg/openvino-model-server:latest \
/ie-serving-py/start_server.sh ie_serving model \
--model_path /opt/ml/model1 --model_name my_model --port 9001

The directory tree structure for /home/rachit/models is

models/
|-- model1/
|---|---1/
|---|---|--- frozen_inference_graph.bin
|---|---|--- frozen_inference_graph.xml

Docker Logs:

2019-04-14 10:36:03,862 - ie_serving.main - INFO - Log level set: INFO
2019-04-14 10:36:03,863 - ie_serving.models.model - INFO - Server start loading model: my_model
2019-04-14 10:36:03,865 - ie_serving.models.model - INFO - List of available versions for my_model model: []
2019-04-14 10:36:03,865 - ie_serving.models.model - INFO - Default version for my_model model is -1
2019-04-14 10:36:03,876 - ie_serving.server.start - INFO - Server listens on port 9001 and will be serving models: ['my_model']

I am a newbie so any help would be really helpful. Thanks

score 0 · Answer 1 · answered Jun 05 '19 at 09:50

Based on the problem description there is incorrect --grpc_address parameter. It should be the IP address of the service exposed in the openvino model server docker container. If you are connecting from the same host, where the docker is started, just use localhost value: python get_serving_meta.py --grpc_address localhost --grpc_port 9001 --model_name my_model --model_version 1

Beside that you need to mind the client proxy settings. In your case http_proxy should be unset or localhost should be included in no_proxy variable.

OpenVINO serving - Servable not found for request

1 Answers1