Intel® Distribution of OpenVINO™ Toolkit
Community assistance about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all aspects of computer vision-related on Intel® platforms.
6502 Discussions

Device with "CPU" name is not registered in the inference's on CPU

ROCK
Novice
1,444 Views

Hi,i'm trying to run gesture_recognition_detection on raspberry pi 4 by using NCS2.

gesture_recognition_detection is combine of two xml download on https://download.01.org/opencv/2020/openvinotoolkit/2020.4/open_model_zoo/models_bin/1

and the model i use are:

1. asl-recognition-0004

2.person-detection-asl-0001

and type following to execute:

python3 gesture_recognition_demo.py \
-m_a /home/user/asl-recognition-0004.xml \
-m_d /home/user/person-detection-asl-0001.xml \
-i 0 \
-c ./msasl100-classes.json

i have check that PATH is currect. But it keep showing error "Device with "CPU" name is not registered in the inference's on CPU"

do anyone know why error occur? 

0 Kudos
7 Replies
ROCK
Novice
1,423 Views

btw i have change the code like this:

python3 gesture_recognition_demo.py \
-m_a /home/user/asl-recognition-0004.xml \
-m_d /home/user/person-detection-asl-0001.xml \
-i 0 \
-d MYRIAD -c ./msasl100-classes.json

 

and the problem would be:

RuntimeError:Failed to compile layer "376/variance/Fused_Add_" : number of biased must equal to number of output channels per group, but :channels per group=1,biased=16

 

0 Kudos
Rizal_Intel
Moderator
1,408 Views

Hi Rock,


You would need to add the argument

-d MYRIAD

for it to work.


It would then select the Neural Compute Stick 2 as to perform the inference. The default device is CPU but the Pi 4 is using ARM architecture which is not compatible with OpenVINO CPU plugin which focuses on Intel processors (which use the x86/AMD64 architecture).


Regards,

Rizal


0 Kudos
ROCK
Novice
1,386 Views

Thanks for your reply.

I had already add the argument in  code like :

python3 gesture_recognition_demo.py \
-m_a /home/user/asl-recognition-0004.xml \
-m_d /home/user/person-detection-asl-0001.xml \
-i 0 \
-d MYRIAD -c ./msasl100-classes.json

 

and the problem would be:

RuntimeError:Failed to compile layer "376/variance/Fused_Add_" : number of biased must equal to number of output channels per group, but :channels per group=1,biased=16

do anyone know how to deal with it ?

0 Kudos
ROCK
Novice
1,370 Views

Sorry again...

I found that the new one reply in 10:02 PM is incorrect. Can MOD help me to delet it?

And th reply that i posted in 09:40 PM was the truely problem i got.

0 Kudos
Adli
Moderator
1,354 Views

Hi ROCK 123,


I have replicated this case and got the same error. We are investigating this issue and will come back to you soon.


Regards,

Adli


0 Kudos
Adli
Moderator
1,347 Views

Hi ROCK 123,

 

Thank you for waiting. The 'asl-recognition' model and 'person-detection-asl' model are not supported on MYRIAD. The models are only supported on CPU and GPU. I apologize for the inconvenience.

 

Regards,

Adli

 

0 Kudos
Adli
Moderator
1,323 Views

Hi ROCK 123,


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


Regards,

Adli


0 Kudos
Reply