- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
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
Link Copied
1 Reply
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
I am also facing the same problem. Did you find the way out?
Reply
Topic Options
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page