Weird crash

Rafek

Hello,

I've encountered very weird crash. So everytime i'm creating a pipeline there is a warning printed to console that openvino 2021.2 is being deprecated. And heres the thing. Once I start a program everything works and suddenly the same message is printed and my OAK-1 lite is being plugged out of my computer.
Here's the warning:

[2024-12-14 19:50:17.731] [depthai] [warning] OpenVINO 2021.2 is deprecated!

Everything works fine and randomly theres error:

[2024-12-14 19:50:17.731] [depthai] [warning] OpenVINO 2021.2 is deprecated!
[18443010C1AA670F00] [1.1.3] [1734202220.172] [host] [warning] Device crashed, but no crash dump could be extracted.
Traceback (most recent call last):
File "my_dir", line 75, in <module>
main(args)
File "my_dir", line 57, in main
frame: dai.ImgFrame = q_detnn_pass.get()
^^^^^^^^^^^^^^^^^^
RuntimeError: Communication exception - possible device error/misconfiguration. Original message 'Couldn't read data from stream: 'detnn_pass' (X_LINK_ERROR)'

Does someone know what is happening?

erik

Hi @Rafek ,
The error you have is either due to connection, or power. How long does it take to throw the error? What's your pipeline like? What depthai version are you using (this also affects stability)?
Openvino deprecation warning shouldn't have such an effect, so these are 2 separate things.
Thanks, Erik

Rafek

The time it throws an error is random, sometimes it takes a few minutes, sometimes a couple of seconds.

My pipeline looks like this

import depthai as dai
from pathlib import Path
import datetime

def create_pipeline() -> dai.Pipeline:
    pipeline: dai.Pipeline = dai.Pipeline()

    #------------------------------------------------------------------
    # declarations
    #-----------------------------------------------------------------
    
    cam_control_xin = pipeline.create(dai.node.XLinkIn)
    cam = pipeline.create(dai.node.ColorCamera)

    detnn = pipeline.create(dai.node.NeuralNetwork)
    detnn_sync = pipeline.create(dai.node.Sync)
    detnn_demux = pipeline.create(dai.node.MessageDemux)
    detnn_out_xout = pipeline.create(dai.node.XLinkOut)
    detnn_pass_xout = pipeline.create(dai.node.XLinkOut)

    manip_img_xin = pipeline.create(dai.node.XLinkIn)
    manip_cfg_xin = pipeline.create(dai.node.XLinkIn)
    manip = pipeline.create(dai.node.ImageManip)
    manip_out_xout = pipeline.create(dai.node.XLinkOut)

    recnn = pipeline.create(dai.node.NeuralNetwork)
    recnn_out_xout = pipeline.create(dai.node.XLinkOut)

    #------------------------------------------------------------------
    # properties
    #------------------------------------------------------------------

    cam.setBoardSocket(dai.CameraBoardSocket.CAM_A)
    cam.setInterleaved(True)
    cam.setPreviewSize(300, 300)
    cam.setResolution(dai.ColorCameraProperties.SensorResolution.THE_1080_P)
    cam.setFps(5)
    cam_control_xin.setStreamName('cam_ctrl')
    
    detnn.setBlobPath((Path('.')/'models'/'vehicle-license-plate-detection-barrier-0106_openvino_2022.1_6shave.blob').resolve().absolute())
    detnn_out_xout.setStreamName('detnn_out')
    detnn_pass_xout.setStreamName('detnn_pass')

    detnn_sync.setSyncThreshold(datetime.timedelta(seconds=0.5))

    
    manip.setWaitForConfigInput(True)
    manip_cfg_xin.setStreamName('manip_cfg')
    manip_img_xin.setStreamName('manip_img')
    manip_out_xout.setStreamName('manip_out')

    recnn.setBlobPath((Path('.')/'models'/'text-recognition-0012_openvino_2021.2_6shave.blob').resolve().absolute())
    recnn_out_xout.setStreamName('recnn_out')

    #------------------------------------------------------------------
    # linking
    #------------------------------------------------------------------

    cam_control_xin.out.link(cam.inputControl)
    cam.preview.link(detnn.input)

    # 1st stage
    detnn.out.link(detnn_sync.inputs['demux_out'])
    detnn.passthrough.link(detnn_sync.inputs['demux_pass'])

    # Syncing
    detnn_sync.out.link(detnn_demux.input)
    detnn_demux.outputs['demux_out'].link(detnn_out_xout.input)
    detnn_demux.outputs['demux_pass'].link(detnn_pass_xout.input)

    # 2nd stage
    manip_cfg_xin.out.link(manip.inputConfig)
    manip_img_xin.out.link(manip.inputImage)
    manip.out.link(recnn.input)
    manip.out.link(manip_out_xout.input)
    recnn.out.link(recnn_out_xout.input)

    return pipeline

jakaskerl

Rafek
Looks like there is a lot of syncing going on. If any of these inputs are blocked the pipeline will halt/crash. Can you try increasing the pool sizes for camera frames (cam.setNumFramesPool()).

Also for debugging, remove the syncing functionality to check if the issue disappears.
Alternatively, sync.setSyncNumAttempts(0) should publish frames as soon as they are filled, which should prevent blocking due to bad sync.

Thanks,
Jaka