load_network fails silently

[Brown_Kramer__Joshua]

I am trying to run a yolov3 model converted from a pytorch model from this repo: https://github.com/ultralytics/yolov3.  Here is my code.  The script simply exits - with no error, warning, or anything - after printing "Loading on device" and before "Reading image".  This is Windows 10, openvino_2021.2.185, Python 3.6.5 (v3.6.5:f59c0932b4, Mar 28 2018, 17:00:18) [MSC v.1900 64 bit (AMD64)] on win32.  Attached are the xml and bin files.

from openvino.inference_engine import IECore, IENetwork

ie = IECore()

print("Reading network")
net = ie.read_network(model="yolov3-master35.xml",weights="yolov3-master35.bin")

print("Loading on device")
exec_net = ie.load_network(network=net, device_name="CPU")

print("Reading image")

[Brown_Kramer__Joshua]

It wouldn't accept the bin file.  Attached is the xml file.

[Brown_Kramer__Joshua]

Here's a link to the .bin file

https://drive.google.com/file/d/1ZbF6EtQUvPUpjJL8xpVAfBvY4ozIx-pq/view?usp=sharing

[Brown_Kramer__Joshua]

Here is an error being thrown when loading the network in c++.  I am running the code _openVino->ExecutableNetwork = _openVino->Core->LoadNetwork(_openVino->Network, "CPU"); and the error is "Exception thrown at 0x00007FFCEAFF7D3B (inference_engine_legacyd.dll) in Ocuvera.CV.Tools.NeuralInferenceTester.exe: 0xC0000005: Access violation reading location 0x0000000000000030."

[Iffa_Intel]

Greetings,

I believe this problem is the same as the one you ha posted here:

https://community.intel.com/t5/Intel-Distribution-of-OpenVINO/YOLOv3-tutorial-doesn-t-work-in-latest-OpenVINO-but-does-work-in/m-p/1251468#M22614

You could go to the thread for the answer.

Thanks!

Sincerely,

Iffa

[Iffa_Intel]

Greetings,

Intel will no longer monitor this thread since we have provided a solution. If you need any additional information from Intel, please submit a new question. 

Sincerely,

Iffa