Model crashes with dynamic shape after loading network

[NewMember]

I converted an onnx squeezenet model to IR using

python3 mo_onnx.py --input_model SSD_nms.onnx --input inputs,top_k_per_class,nms_iou,nms_score --input_shape [1,3,224,224],[1],[1],[1]

This step worked fine, but when I try to load the network it gives me the following error.

ie = IECore() 
net = ie.read_network(model=model_path, weights=weights_path)
print (net.layers)

File "ie_api.pyx", line 1170, in openvino.inference_engine.ie_api.IENetwork.layers.__get__ ValueError: get_shape was called on a descriptor::Tensor with dynamic shape

IR definition of the troublesome layer:

<layer id="351" name="selected_indices" type="NonMaxSuppression" version="opset1">
    <data box_encoding="center" sort_result_descending="0"/>
    <input>
        <port id="0">
            <dim>1</dim>
            <dim>10000</dim>
            <dim>4</dim>
        </port>
        <port id="1">
            <dim>1</dim>
            <dim>2</dim>
            <dim>10000</dim>
        </port>
        <port id="2"/>
        <port id="3"/>
        <port id="4"/>
    </input>
    <output>
        <port id="5" precision="I64">
            <dim>10000</dim>
            <dim>3</dim>
        </port>
    </output>
</layer>

Any help would be much appreciated. 

[Munesh_Intel · Accepted solution]

Hi Aravind,

Inference Engine supports NonMaxSuppression layer by CPU plugin (via Extensibility mechanism) and also by Shape Inference feature.

More information is available at the following pages:

https://docs.openvinotoolkit.org/2020.4/openvino_docs_IE_DG_supported_plugins_Supported_Devices.html#supported_layers

https://docs.openvinotoolkit.org/2020.4/openvino_docs_IE_DG_Extensibility_DG_Intro.html

https://docs.openvinotoolkit.org/2020.4/openvino_docs_IE_DG_ShapeInference.html

Regards,

Munesh