frame

Howdy, Stranger!

It looks like you're new here. If you want to get involved, click one of these buttons!

Sign In

Howdy, Stranger!

It looks like you're new here. If you want to get involved, click one of these buttons!

Help using res10 ssd for face detection

Hi,
I tried to use caffemodel used by OpenCV dnn face detector (here).
When I use mvNCCheck then NCS hangs after inferencing:


mvNCCheck deploy.prototxt -w res10_300x300_ssd_iter_140000.caffemodel -s 12 -is 300 300 -cs 2,1,0
/usr/lib/python3.5/importlib/_bootstrap.py:222: RuntimeWarning: compiletime version 3.4 of module 'tensorflow.python.framework.fast_tensor_util' does not match runtime version 3.5
return f(*args, **kwds)
/usr/lib/python3.5/importlib/_bootstrap.py:222: RuntimeWarning: builtins.type size changed, may indicate binary incompatibility. Expected 432, got 412
return f(*args, **kwds)
mvNCCheck v02.00, Copyright @ Intel Corporation 2017

/usr/local/bin/ncsdk/Controllers/FileIO.py:65: UserWarning: You are using a large type. Consider reducing your data sizes for best performance
Blob generated
USB: Transferring Data...
/usr/local/lib/python3.5/dist-packages/mvnc/mvncapi.py:420: DeprecationWarning: The binary mode of fromstring is deprecated, as it behaves surprisingly on unicode inputs. Use frombuffer instead
USB: Myriad Execution Finished
USB: Myriad Connection Closing.
E: [ 0] dispatcherEventReceive:200 dispatcherEventReceive() Read failed -1

^CSegmentation fault


I tried also to compile the graph and inferencing: same result.

Comments

  • 6 Comments sorted by Votes Date Added
  • @saveriop Hi, just wondering if this is in a virtual machine (on windows 10) or physical machine and which NCSDK version you are using. Thanks.

  • Hi,
    I have the same issue.

    My machine: Raspberry Pi 3 Model B
    Kernel version: Linux SPEAKER-1 4.14.30-v7+
    OS version: 9.4 (stretch)

    NCSDK version: 2.05

    I will appreciate any help with this error.

    Thanks!

  • Hi,
    it happens in every situation. I tried on Ubuntu 16.04 & 18.04 physical, Ubuntu 16.04 virtual both on Windows and Ubuntu host, in raspberry pi 3.

  • Hello,
    I have the same issue.

    My machine: Win10
    VM: VirtualBox 5.2.14

    NCSDK version: 2.05

    I will appreciate any help with this error.

    Thanks!

  • @saveriop @renhanchi @Slavastas Thanks for reporting this. I tried running the same network on my bench and it seems to hang with a dispatchEventReceived() Read error -4 error and then hangs. The same issue seemed to occur when I tested another user's custom resnet50 model. I am not sure if it is related or what the root cause is, but if I make any progress I'll give you guys an update. Thanks.

  • Encountering a similar error so I went ahead and put the device in verbose logging mode
    ( - global_set_option(movi.GlobalOption.RW_LOG_LEVEL, 0) ) and did trace (see below) to see if it helps in the troubleshooting process. Critical error in my project so any help or thoughts would be greatly appreciated

    Thank you!!!

    TRACE

    INFO] Get Tensor Descriptor Structures
    [INFO] create input and output Fifos
    I: [ 0] ncFifoCreate:2126 Init fifo
    I: [ 0] ncFifoCreate:2126 Init fifo
    I: [ 0] ncFifoAllocate:2321 Creating fifo
    I: [ 0] ncFifoAllocate:2321 Creating fifo
    [INFO] return input and output Fifos
    [INFO] Sending Image to NCS device]
    D: [ 0] ncFifoWriteElem:2592 No layout conversion is needed 0

    D: [ 0] convertDataTypeAndLayout:170 src data type 1 dst data type 0

    D: [ 0] convertDataTypeAndLayout:172 SRC: w 300 h 300 c 3 w_s 12 h_s 3600 c_s 4

    D: [ 0] convertDataTypeAndLayout:174 DST: w 300 h 300 c 3 w_s 6 h_s 1800 c_s 2

    D: [ 0] ncFifoWriteElem:2617 write count 0 num_elements 2 userparam 0x75a86418

    [INFO Sendiing to NCS Queue]
    I: [ 0] ncGraphQueueInference:3048 trigger start

    I: [ 0] ncGraphQueueInference:3145 trigger end

    D: [ 0] ncFifoReadElem:2686 No layout conversion is needed 0

    D: [ 0] convertDataTypeAndLayout:170 src data type 0 dst data type 1

    D: [ 0] convertDataTypeAndLayout:172 SRC: w 7 h 201 c 1 w_s 2 h_s 14 c_s 2

    D: [ 0] convertDataTypeAndLayout:174 DST: w 7 h 201 c 1 w_s 4 h_s 28 c_s 4

    D: [ 0] ncFifoReadElem:2714 num_elements 2 userparam 0x75a86558 output length 5628

    [INFO] Image prdictions returned from NCS
    1
    1
    [INFO] Sending Image to NCS device]
    D: [ 0] ncFifoWriteElem:2592 No layout conversion is needed 0

    D: [ 0] convertDataTypeAndLayout:170 src data type 1 dst data type 0

    D: [ 0] convertDataTypeAndLayout:172 SRC: w 300 h 300 c 3 w_s 12 h_s 3600 c_s 4

    D: [ 0] convertDataTypeAndLayout:174 DST: w 300 h 300 c 3 w_s 6 h_s 1800 c_s 2

    D: [ 0] ncFifoWriteElem:2617 write count 1 num_elements 2 userparam 0x75a86418

    [INFO Sendiing to NCS Queue]
    I: [ 0] ncGraphQueueInference:3048 trigger start

    E: [ 0] dispatcherEventReceive:200 dispatcherEventReceive() Read failed -1

Sign In or Register to comment.