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!

mvNCcheck fails when I was trying to check mobilenet ssd

mvNCcheck fails when I was trying to check mobilenet ssd. Is there anyone run mobilenet ssd succcessfully with the latest 1.11 NCSDK release?
the command I used: "mvNCCheck MobileNetSSD_deploy.prototxt -w MobileNetSSD_deploy.caffemodel -s 12 -is 300 300 -i /opt/movidius/ncappzoo/data/images/512_Monitor.jpg"
the caffemodel and prototxt are from https://github.com/chuanqi305/MobileNet-SSD.
the error message is as follows:
mvNCCheck v02.00, Copyright @ Movidius Ltd 2016

/usr/local/lib/python3.5/dist-packages/scipy/lib/decorator.py:219: DeprecationWarning: inspect.getargspec() is deprecated, use inspect.signature() instead
first = inspect.getargspec(caller)[0][0] # first arg
/usr/local/lib/python3.5/dist-packages/scipy/optimize/nonlin.py:1498: DeprecationWarning: inspect.getargspec() is deprecated, use inspect.signature() instead
args, varargs, varkw, defaults = inspect.getargspec(jac.init)
/usr/local/lib/python3.5/dist-packages/scipy/stats/_distn_infrastructure.py:611: DeprecationWarning: inspect.getargspec() is deprecated, use inspect.signature() instead
sign = inspect.getargspec(self._stats)
/usr/local/lib/python3.5/dist-packages/scipy/stats/_distn_infrastructure.py:648: DeprecationWarning: inspect.getargspec() is deprecated, use inspect.signature() instead
shapes_args = inspect.getargspec(meth)
/usr/local/bin/ncsdk/Controllers/FileIO.py:52: UserWarning: You are using a large type. Consider reducing your data sizes for best performance
"Consider reducing your data sizes for best performance\033[0m")
USB: Transferring Data...
USB: Myriad Execution Finished
USB: Myriad Connection Closing.
USB: Myriad Connection Closed.
Result: (1, 25, 7)
1) 44 nan
2) 9 nan
3) 23 nan
4) 30 nan
5) 149 nan
Expected: (1, 1, 7)
1) 1 20.0
2) 2 0.99951
3) 5 0.99219
4) 6 0.9126
5) 3 0.059631
/usr/local/bin/ncsdk/Controllers/Metrics.py:75: RuntimeWarning: invalid value encountered in greater

diff)) / total_values * 100

Obtained values

Obtained Min Pixel Accuracy: nan% (max allowed=2%), Fail
Obtained Average Pixel Accuracy: nan% (max allowed=1%), Fail
Obtained Percentage of wrong values: 1700.0% (max allowed=0%), Fail
Obtained Pixel-wise L2 error: nan% (max allowed=1%), Fail

Obtained Global Sum Difference: nan

Comments

  • 3 Comments sorted by Votes Date Added
  • I tried to run inference with the compiled graph file and get result of length 707, some values are inf or nan.
    The following is the script I ran:
    dim=(300, 300)

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

    devices = mvnc.EnumerateDevices()

    device = mvnc.Device(devices[0])

    device.OpenDevice()

    network_blob="/home/intel/workspace/ncappzoo/caffe/MobileNetSSD/graph"

    with open(network_blob, mode="rb") as f:
    blob = f.read()

    graph = device.AllocateGraph(blob)

    img = cv2.imread("/home/intel/workspace/ncappzoo/data/images/cat.jpg")
    img = cv2.resize(img, dim)
    img = np.subtract(img, 127.5)
    img = np.multiply(img, 0.007843)

    graph.LoadTensor(img.astype(np.float16), 'user object')
    output, userobj = graph.GetResult()
    print (len(output))

    print (output)

    graph.DeallocateGraph()
    device.CloseDevice()

  • some of the results as follows:
    2.50000000e+01 8.13125000e+01 5.33203125e+00 4.25312500e+01
    8.11219215e-05 8.03125000e+01 8.53125000e+01 0.00000000e+00
    1.00000000e+00 nan -inf -5.27187500e+01
    inf -5.27187500e+01 0.00000000e+00 2.00000000e+00
    nan -inf -5.27187500e+01 inf
    -5.27187500e+01 0.00000000e+00 3.00000000e+00 nan
    -inf -5.27187500e+01 inf -5.27187500e+01
    0.00000000e+00 4.00000000e+00 nan -inf
    -5.27187500e+01 inf -5.27187500e+01 0.00000000e+00
    5.00000000e+00 nan -inf -5.27187500e+01
    inf -5.27187500e+01 0.00000000e+00 6.00000000e+00
    nan -inf -5.27187500e+01 inf
    -5.27187500e+01 0.00000000e+00 7.00000000e+00 nan
    -inf -5.27187500e+01 inf -5.27187500e+01
    0.00000000e+00 8.00000000e+00 nan -inf
    -5.27187500e+01 inf -5.27187500e+01 0.00000000e+00
    8.00000000e+00 1.00000000e+00 5.37109375e-03 -2.92968750e-03
    9.48242188e-01 9.67285156e-01 0.00000000e+00 9.00000000e+00
    nan -inf -5.27187500e+01 inf
    -5.27187500e+01 0.00000000e+00 1.00000000e+01 nan
    -inf -5.27187500e+01 inf -5.27187500e+01
    0.00000000e+00 1.10000000e+01 nan -inf
    -5.27187500e+01 inf -5.27187500e+01 0.00000000e+00
    1.20000000e+01 nan -inf -5.27187500e+01
    inf -5.27187500e+01 0.00000000e+00 1.30000000e+01
    nan -inf -5.27187500e+01 inf
    -5.27187500e+01 0.00000000e+00 1.40000000e+01 nan
    -inf -5.27187500e+01 inf -5.27187500e+01
    0.00000000e+00 1.50000000e+01 nan -inf

  • I face the same problem. Have you solved it?@xhuan28

Sign In or Register to comment.