It is support object_detection_sample_ssd python code from openvino R3. I run object_detection_sample_ssd of python and C++ version with the same xml and bin file . It works in C++ sample code, but fail in python code.
below is the error message:
[ ERROR ] Following layers are not supported by the plugin for specified device
proposals, all_class_predictions_with_background, detection_output
[ ERROR ] Please try to specify cpu extensions library path in sample's command
line parameters using -l or --cpu_extension command line argument
Yes you must first execute build_samples_msvc.bat (or *.sh in the case of Linux). This step will build the cpu extensions library. Then you have to pass in the full path to the cpu extensions library via -l
-l CPU_EXTENSION, --cpu_extension CPU_EXTENSION
Optional. Required for CPU custom layers. Absolute
path to a shared library with the kernels
In fact if you do a --h to object_detection_sample_ssd.py you will see mention of the -l switch.
Also you didn't mention which version you are using but I hope you've upgraded to OpenVino 2019R3.
Hope it helps,
I have another problem in object_detection_sample_ssd.py. I run this python file and show below error message.
File "object_detection_sample_ssd.py", line 84, in main
n, c, h, w = net.inputs[input_blob].shape
ValueError: not enough values to unpack (expected 4, got 2)
But ,I use the same xml file in the object_detection_sample_ssd C++ code, it is ok.