Community
cancel
Showing results for 
Search instead for 
Did you mean: 
Highlighted
Community Manager
295 Views

GetResult raise Exception(Status(status)) Exception: mvncStatus.MYRIAD_ERROR

I have a TensorFlow model that I was able to train, test, freeze, and cross compile to the NCS. I can load the graph onto the NCS, but when I try to call GetResult, I get the following error which I don't know how to decode or solve:

 

l03:~/workspace/movidius$ python3 ./run_detector.py

 

./run_detector.py:18: DeprecationWarning: "LOGLEVEL" is deprecated. Please use "LOG_LEVEL"!

 

mvnc.SetGlobalOption(mvnc.GlobalOption.LOGLEVEL, 2)

 

Device 0 Address: 3 - VID/PID 03e7:2150

 

Starting wait for connect with 2000ms timeout

 

Found Address: 3 - VID/PID 03e7:2150

 

Found EP 0x81 : max packet size is 512 bytes

 

Found EP 0x01 : max packet size is 512 bytes

 

Found and opened device

 

Performing bulk write of 865724 bytes…

 

Successfully sent 865724 bytes of data in 73.488857 ms (11.234611 MB/s)

 

Boot successful, device address 3

 

Device 0 Address: 5 - VID/PID 03e7:f63b

 

Found Address: 5 - VID/PID 03e7:f63b

 

done

 

Booted 5 -> VSC

 

testdatastack shape (17, 256, 800, 5)

 

testdata shape (256, 256, 5)

 

tensor load to device complete

 

Traceback (most recent call last):

 

File "./run_detector.py", line 42, in

 

output, userobj, status = graph.GetResult()

 

File "/usr/local/lib/python3.5/dist-packages/mvnc/mvncapi.py", line 264, in GetResult

 

raise Exception(Status(status))

 

Exception: mvncStatus.MYRIAD_ERROR

 

I have posted the training script, freezing script, protobuf file, run script, and cross compiled model at:

 

https://drive.google.com/drive/folders/1zJf9nQCY2_wNPK9R9AGKQA8YvvxL8CIS?usp=sharing
0 Kudos
1 Reply
Highlighted
Community Manager
27 Views

Hi,

 

I am also facing the same problem. Did you find the way out?
0 Kudos