topic Quote:Cary P. (Intel) wrote: in Intel® Distribution of OpenVINO™ Toolkit

ie.load_network() crashes ny notebook

Raza__Ghulam_Jilani — Mon, 25 Nov 2019 15:46:21 GMT

ive converted a yolo v3 model to ir format and i am writing a python script to run it via inference engine on my cpu. but every time i run the script, the line

exec_net = ie.load_network(network=net, device_name='CPU')

crashes the notebook. Anyone else facing the same problem?

Hi, Ghulam Jilani,

Cary_P_Intel1 — Tue, 26 Nov 2019 05:43:40 GMT

Hi, Ghulam Jilani,

Can you provide the dummy code which can reduplicate your issue? Otherwise, it's hard to identify where the problem is.

Quote:Cary P. (Intel) wrote:

Raza__Ghulam_Jilani — Tue, 26 Nov 2019 11:59:04 GMT

Cary P. (Intel) wrote:
Hi, Ghulam Jilani,
Can you provide the dummy code which can reduplicate your issue? Otherwise, it's hard to identify where the problem is.

!Update!

i managed to ditch the script on my pc by running the demo object_detection_demo_yolov3_async.py and supplying it with my model, it worked fine, but now i need to run it on different edge nodes and i got the access to intel dev cloud, so i uploaded the model there and I literally copy pasted the code from the same demo (excluding the app flags and main program structure ofcourse just the straight forward model running code) and the online notebook crashes at exec_net = ie.load_network(network=net, num_requests=2, device_name=device) statement without any warning or error. my converted model can be found in below link. Code is from the openvino demo object_detection_demo_yolov3_async.py

https://drive.google.com/drive/folders/1_sRkq8y-Ijdfb9D_kzw8ozsMIM48v17T?usp=sharing