Faster R-CNN Inception V2 custom trained, conversion in OV 1.1.

[Pise__Abhijeet]

Hi,

I am using Openvino R1.1 to convert a custom trained faster rcnn inception v2 model.

I have used the models zoo as a checkpoint with reduced no of classes. I am using TF 1.14 for training and I have TF 1.15 in the OpenVino envt.

I am able to generate the .bin and .xml files. However when i am running inference, using the below lines

plugin_dir = r'C:\Program Files (x86)\IntelSWTools\openvino_2019.1.148\deployment_tools\inference_engine\bin\intel64\Release' 
model_xml = '.\frozen_inference_graph.xml' 
model_bin = '.\frozen_inference_graph.bin' 

plugin = IEPlugin("CPU")
plugin.add_cpu_extension(r"C:\Program Files (x86)\IntelSWTools\openvino_2019.1.148\deployment_tools\inference_engine\bin\intel64\Release\cpu_extension_avx2.dll")

net = IENetwork(model=model_xml, weights=model_bin)

I get the below error:

Traceback (most recent call last):
  File "infer.py", line 15, in <module>
    net = IENetwork(model=model_xml, weights=model_bin)
  File "ie_api.pyx", line 271, in openvino.inference_engine.ie_api.IENetwork.__cinit__
RuntimeError: Error reading network: in Layer FirstStageFeatureExtractor/InceptionV2/InceptionV2/Conv2d_1a_7x7/Relu: trying to connect an edge to non existing output port: 8.5

I would be grateful if you could help.

[Pise__Abhijeet]

Also, what purpose do the other json files with versions in extensions\front\tf folder serve? I am using faster_rcnn_support.json 

[Munesh_Intel · Accepted solution]

Hi Abhijeet,

Thanks for reaching out. 

I would suggest you use Intel® Distribution of OpenVINO™ Toolkit version 2020.3 LTS, which is a vastly improved version with latest features and leading performance.

As for your question regarding the .json files, the <INSTALL_DIR>/deployment_tools/model_optimizer/extensions/front/tf directory contains .json files for the models downloaded from the TensorFlow Object Detection API zoo.

More information can be obtained at the following page:

https://docs.openvinotoolkit.org/2020.3/_docs_MO_DG_prepare_model_convert_model_tf_specific_Convert_Object_Detection_API_Models.html#how_to_convert_a_model

Regards,

Munesh

[Pise__Abhijeet]

Thank you Munesh for your prompt response.