Error while running sample model (StereoPi with CM3+)

[Rezohlazov__Vladysla]

My configuration:

StereoPi (carries Compute Module 3 as in Raspberry Pi 3B+)

Intel NCS2

I have Raspbian 10 (buster) installed on my RPi.

I installed OpenVINO Toolkit (version 2020.3, API v2.1) without any issues as described in a basic guide for raspbian and tried to run sample model object_detection_sample_ssd. When I run it, I get this issue (terminate called without an active exception Aborted):

pi@raspberrypi:~/robot/build $ ./armv7l/Release/object_detection_sample_ssd -m face-detection-adas-0001.xml -d MYRIAD -i /home/pi/robot/images/face.jpg
[ INFO ] InferenceEngine:
    API version ............ 2.1
    Build .................. 2020.3.0-3467-15f2c61a-releases/2020/3
    Description ....... API
Parsing input parameters
[ INFO ] Files were added: 1
[ INFO ]     /home/pi/robot/images/face.jpg
[ INFO ] Loading Inference Engine
[ INFO ] Device info:
    MYRIAD
    myriadPlugin version ......... 2.1
    Build ........... 2020.3.0-3467-15f2c61a-releases/2020/3
[ INFO ] Loading network files:
    face-detection-adas-0001.xml
    face-detection-adas-0001.bin
terminate called without an active exception
Aborted

Also, I tried different (FP16, FP16-INT8, etc.). Find nothing in the internet or the Intel forum. What is the problem with?

[RandallMan_B_Intel]

Hi Vladyslav,

I tried to run with the 2019 R3 models and it works. Try again with the models from open_model_zoo 2019 R3.

https://download.01.org/opencv/2019/open_model_zoo/R3/20190905_163000_models_bin/

Let me know if the issue persists.

Regards,

Randall.

[Rezohlazov__Vladysla]

Hi Randall!

I tried to run the model you proposed and got another error:

pi@raspberrypi:~/robot/build $ ./armv7l/Release/object_detection_sample_ssd -d MYRIAD -i /home/pi/robot/images/2.jpg -m face-detection-adas-0001.xml
[ INFO ] InferenceEngine:
    API version ............ 2.1
    Build .................. 2020.3.0-3467-15f2c61a-releases/2020/3
    Description ....... API
Parsing input parameters
[ INFO ] Files were added: 1
[ INFO ]     /home/pi/robot/images/2.jpg
[ INFO ] Loading Inference Engine
[ INFO ] Device info:
    MYRIAD
    myriadPlugin version ......... 2.1
    Build ........... 2020.3.0-3467-15f2c61a-releases/2020/3
[ INFO ] Loading network files:
    face-detection-adas-0001.xml
    face-detection-adas-0001.bin
[ INFO ] Preparing input blobs
[ INFO ] Batch size is 1
[ INFO ] Preparing output blobs
[ INFO ] Loading model to the device
[ INFO ] Create infer request
[ WARNING ] Image is resized from (1000, 667) to (672, 384)
[ INFO ] Batch size is 1
[ INFO ] Start inference
[ INFO ] Processing output blobs
corrupted double-linked list
Aborted

Also, I get another errors by using various input pictures.

[RandallMan_B_Intel]

Hi Vladyslav,

We are currently looking into your issue and we will come back to you as soon as possible.

Regards,

Randall.

[RandallMan_B_Intel]

Hi Vladyslav,

Please try to downgrade to the OpenVINO toolkit 2019 R3.

https://download.01.org/opencv/2019/openvinotoolkit/R3/

Regards,

Randall.

[Rezohlazov__Vladysla]

OpenVINO 2019 R3 works perfectly as expected. Thanks for the good advice!

[RandallMan_B_Intel]

Hi Vladyslav,

I am glad to hear your problem is resolved. Have a nice day!

Regards,

Randall.