Problem occur while to optimize onnx model

[wang__zyu]

 sudo python3 mo.py --input_model ~/fasterRCNN/s2g_api_v3_b3_fpn.onnx [sudo] password for openvino:
Model Optimizer arguments:
Common parameters:
    - Path to the Input Model:     /home/openvino/fasterRCNN/s2g_api_v3_b3_fpn.onnx
    - Path for generated IR:     /opt/intel/computer_vision_sdk_2018.3.343/deployment_tools/model_optimizer/.
    - IR output name:     s2g_api_v3_b3_fpn
    - Log level:     ERROR
    - Batch:     Not specified, inherited from the model
    - Input layers:     Not specified, inherited from the model
    - Output layers:     Not specified, inherited from the model
    - Input shapes:     Not specified, inherited from the model
    - Mean values:     Not specified
    - Scale values:     Not specified
    - Scale factor:     Not specified
    - Precision of IR:     FP32
    - Enable fusing:     True
    - Enable grouped convolutions fusing:     True
    - Move mean values to preprocess section:     False
    - Reverse input channels:     False
ONNX specific parameters:
Model Optimizer version:     1.2.185.5335e231
[ ERROR ]  Unexpected exception happened during extracting attributes for node 345.
Original exception message: Upsample scales attribute is defined for node 464. Only scale_width and scale_height are supported.

I want to figure out what is going on here, and how can I fix it?

Thanks for helping!

[Severine_H_Intel]

Dear Zyu, 

can you provide the model such as we reproduce the issue ?

Best, 

Severine

[wang__zyu]

Habert, Severine (Intel) (Intel) wrote:

Dear Zyu, 

can you provide the model such as we reproduce the issue ?

Best, 

Severine

Hi, Habert, Thank you very much to reply my issue, I have fixed this already, because there is some unsupported ops in my model.

Now I am facing a new issue. I have got a NCS2 yesterday by taking part in AIDS, but when I use it to inference model, I haven't feel any speed up comparing with the NCS. I am using the openVINO-R4, SSD-mobilenet2 model, follow by the workflow. And I gain 12fps on NCS , 13fps on NCS2. Hopping for your help!Thanks again!