Error while inferencing using OpenVINO

[RahulSharma]

I encountered following error while inferencing using Intel OpenVINO(2021.4) and my custom model for audio emotion classification:

Command run:  python3 sp_classification.py --model /home/ubuntu/Desktop/SER/mlp_classifier_3_classes/ir_files/saved_model.xml --weights /home/ubuntu/Desktop/SER/mlp_classifier_3_classes/ir_files/saved_model.bin --input /home/ubuntu/Desktop/SER/0_agent_happy.wav

[ INFO ] Creating Inference Engine
[ INFO ] Reading the network: /home/ubuntu/Desktop/SER/mlp_classifier_3_classes/ir_files/saved_model.xml
[ INFO ] Loading the model to the plugin
Traceback (most recent call last):
File "sp_classification.py", line 148, in <module>
sys.exit(main())
File "sp_classification.py", line 132, in main
exec_net = ie.load_network(network=net, device_name=args.device)
File "ie_api.pyx", line 314, in openvino.inference_engine.ie_api.IECore.load_network
File "ie_api.pyx", line 323, in openvino.inference_engine.ie_api.IECore.load_network
RuntimeError: FullyConnected shape is incorrect

I am attaching sp_classification.py(int txt format since .py is not supported) and model bin, xml and mapping file for refrence. Can anyone please tell me why I am getting this RuntimeError?

[IntelSupport]

Hi Rahul Sharma,

Thanks for reaching out. Could you share the original model for us to further investigate this issue? Also, please provide the source of your audio emotion classification.

Regards,

Aznie

[IntelSupport]

Hi Rahul Sharma,

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,

Aznie