raspberry pi 3+ B and live image app

[idata]

Hi expert

I have installed ncsdk v1 and trying to run the live -image-classifier-picam. Unfortunately I get the error message below. Any hints?

making gendernet

(cd ../../caffe/GenderNet; make compile;)make[1]: Entering directory '/home/pi/ncappzoo/caffe/GenderNet'make[2]: Entering directory '/home/pi/ncappzoo/data/age_gender'Traceback (most recent call last): File "convert_mean.py", line 3, in import caffe File "/opt/movidius/caffe/python/caffe/init.py", line 1, in from .pycaffe import Net, SGDSolver, NesterovSolver, AdaGradSolver, RMSPropSolver, AdaDeltaSolver, AdamSolver File "/opt/movidius/caffe/python/caffe/pycaffe.py", line 15, in import caffe.io File "/opt/movidius/caffe/python/caffe/io.py", line 2, in import skimage.io File "/usr/local/lib/python3.5/dist-packages/skimage/init.py", line 177, in from .data import data_dir File "/usr/local/lib/python3.5/dist-packages/skimage/data/init.py", line 15, in from ..io import imread, use_plugin File "/usr/local/lib/python3.5/dist-packages/skimage/io/init.py", line 7, in from .manage_plugins import * File "/usr/local/lib/python3.5/dist-packages/skimage/io/manage_plugins.py", line 28, in from .collection import imread_collection_wrapper File "/usr/local/lib/python3.5/dist-packages/skimage/io/collection.py", line 14, in from ..external.tifffile import TiffFile File "/usr/local/lib/python3.5/dist-packages/skimage/external/tifffile/init.py", line 1, in from .tifffile import imsave, imread, imshow, TiffFile, TiffWriter, TiffSequence File "/usr/local/lib/python3.5/dist-packages/skimage/external/tifffile/tifffile.py", line 293, in from . import _tifffileRuntimeError: module compiled against API version 0xc but this version of numpy is 0xbMakefile:5: recipe for target 'all' failedmake[2]: *** [all] Error 1make[2]: Leaving directory '/home/pi/ncappzoo/data/age_gender'Makefile:17: recipe for target 'prereqs' failedmake[1]: *** [prereqs] Error 2make[1]: Leaving directory '/home/pi/ncappzoo/caffe/GenderNet'Makefile:11: recipe for target 'gendernet' failedmake: *** [gendernet] Error 2

Thanks,

sojohan

[idata]

@sojohan

$ sudo pip3 install numpy scikit-image --upgrade

[idata]

Hi Pinto

Thanks one step further, but now I get the error below:

mvNCCompile v02.00, Copyright @ Movidius Ltd 2016

/usr/lib/python3/dist-packages/scipy/_lib/_numpy_compat.py:10: DeprecationWarning: Importing from numpy.testing.nosetester is deprecated, import from numpy.testing instead.

from numpy.testing.nosetester import import_nose/usr/lib/python3/dist-packages/scipy/stats/morestats.py:16: DeprecationWarning: Importing from numpy.testing.decorators is deprecated, import from numpy.testing instead. from numpy.testing.decorators import setastest/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")make[1]: Leaving directory '/home/pi/ncappzoo/caffe/AgeNet'

Running live-image-classifier.py

python3 live-image-classifier.py --graph ../../caffe/AgeNet/graph --labels ../../data/age_gender/age_categories.txtpython3: can't open file 'live-image-classifier.py': [Errno 2] No such file or directoryMakefile:41: recipe for target 'run' failedmake: *** [run] Error 2

Thanks,

sojohan

[idata]

@sojohan

The following can be ignored.

/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")

live-image-classifier.py is in the following location.

$ mkdir -p ~/workspace $ cd ~/workspace $ git clone https://github.com/movidius/ncappzoo $ cd ~/workspace/ncappzoo/apps/live-image-classifier/ $ make run

[idata]

Hi pinto

The same error:

/usr/lib/python3/dist-packages/scipy/_lib/_numpy_compat.py:10: DeprecationWarning: Importing from numpy.testing.nosetester is deprecated, import from numpy.testing instead.

from numpy.testing.nosetester import import_nose/usr/lib/python3/dist-packages/scipy/stats/morestats.py:16: DeprecationWarning: Importing from numpy.testing.decorators is deprecated, import from numpy.testing instead. from numpy.testing.decorators import setastest/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")make[1]: Leaving directory '/home/pi/workspace/ncappzoo/caffe/AgeNet'

Running live-image-classifier.py

python3 live-image-classifier.py --graph ../../caffe/AgeNet/graph --labels ../../data/age_gender/age_categories.txtpython3: can't open file 'live-image-classifier.py': [Errno 2] No such file or directoryMakefile:41: recipe for target 'run' failedmake: *** [run] Error 2

[idata]

@sojohan

Please move to the path where live-image-classifier.py exists and execute it.

Python3 can not find the live-image-classifier.py file.Ignore the No devices found error.$ git clone https://github.com/movidius/ncappzoo $ cd ~/ncappzoo/apps/live-image-classifier/ $ ls -lh -rw-rw-r-- 1 xxxx xxxx 87 10月 29 00:17 AUTHORS.txt -rw-rw-r-- 1 xxxx xxxx 1.3K 10月 29 00:17 Makefile -rw-rw-r-- 1 xxxx xxxx 2.9K 10月 29 00:17 README.md -rw-rw-r-- 1 xxxx xxxx 6.2K 10月 29 00:17 live-image-classifier.py -rw-rw-r-- 1 xxxx xxxx 13K 10月 29 00:17 screen_shot.jpg $ make run making gendernet (cd ../../caffe/GenderNet; make compile;) make[1]: ディレクトリ '/home/xxxx/git/ncappzoo/caffe/GenderNet' に入ります make[2]: ディレクトリ '/home/xxxx/git/ncappzoo/data/age_gender' に入ります : : : mvNCCompile -w age_net.caffemodel -s 12 deploy.prototxt /usr/local/bin/ncsdk/Controllers/Parsers/TensorFlowParser/Convolution.py:46: SyntaxWarning: assertion is always true, perhaps remove parentheses? assert(False, "Layer type not supported by Convolution: " + obj.type) /usr/local/bin/ncsdk/Controllers/Parsers/Phases.py:322: SyntaxWarning: assertion is always true, perhaps remove parentheses? assert(len(pred) == 1, "Slice not supported to have >1 predecessors") mvNCCompile v02.00, Copyright @ Intel Corporation 2017 Fusing Pad and Convolution2D Fusing BatchNorm and Scale after Convolution Replacing BN with Bias&Scale Fusing Permute and Flatten Fusing Eltwise and Relu Eliminate layers that have been parsed as NoOp Evaluating input and weigths for each hw layer -------------------------------------- ---------------------- ---------------------- # Network Input tensors ['data#20'] # Network Output tensors ['prob#32'] Blob generated make[1]: ディレクトリ '/home/xxxx/git/ncappzoo/caffe/AgeNet' から出ます Running live-image-classifier.py python3 live-image-classifier.py --graph ../../caffe/AgeNet/graph --labels ../../data/age_gender/age_categories.txt No devices found #<--- Please ignore. `live-image-classifier.py` has been successfully called.

[idata]

I get:

totalt 36K-rw-r--r-- 1 pi pi 87 okt 27 16:29 AUTHORS.txt-rwxrwxrwx 1 pi pi 6,1K okt 27 16:29 live-image-classifier.py-rw-r--r-- 1 pi pi 1,3K okt 27 16:29 Makefile-rw-r--r-- 1 pi pi 2,9K okt 27 16:29 README.md-rw-r--r-- 1 pi pi 13K okt 27 16:29 screen_shot.jpg

When I use make run, i get:

mvNCCompile -w age_net.caffemodel -s 12 deploy.prototxtmvNCCompile v02.00, Copyright @ Movidius Ltd 2016

/usr/lib/python3/dist-packages/scipy/_lib/_numpy_compat.py:10: DeprecationWarning: Importing from numpy.testing.nosetester is deprecated, import from numpy.testing instead.

from numpy.testing.nosetester import import_nose/usr/lib/python3/dist-packages/scipy/stats/morestats.py:16: DeprecationWarning: Importing from numpy.testing.decorators is deprecated, import from numpy.testing instead. from numpy.testing.decorators import setastest/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")make[1]: Leaving directory '/home/pi/workspace/ncappzoo/caffe/AgeNet'

Running live-image-classifier.py

python3 live-image-classifier.py --graph ../../caffe/AgeNet/graph --labels ../../data/age_gender/age_categories.txtOpenCV Error: Assertion failed (ssize.width > 0 && ssize.height > 0) in resize, file /home/pi/opencv-3.3.0/modules/imgproc/src/imgwarp.cpp, line 3483Traceback (most recent call last): File "live-image-classifier.py", line 189, in main() File "live-image-classifier.py", line 127, in main img = pre_process_image( frame ) File "live-image-classifier.py", line 60, in pre_process_image img = cv2.resize( frame, tuple( ARGS.dim ) )cv2.error: /home/pi/opencv-3.3.0/modules/imgproc/src/imgwarp.cpp:3483: error: (-215) ssize.width > 0 && ssize.height > 0 in function resize

Makefile:41: recipe for target 'run' failed

make: *** [run] Error 1

[idata]

@sojohan

Good morning.

Is the USB camera connected?

It looks just as if no image was entered.From here on, it is not a category of NCSDK, it is a problem of control of OpenCV and USB Camera.camera = cv2.VideoCapture( ARGS.video ) error: (-215) ssize.width > 0 && ssize.height > 0 in function resize

A command to check the connection information of the USB camera.

$ sudo ls /dev | grep video video0 #<- ARGS.video = 0 video1 #<- ARGS.video = 1 video2 #<- ARGS.video = 2

Is the resolution specification of the USB camera compatible with Width = 620, Height = 480?

If it does not correspond, adjust the following numbers according to the specifications of your USB camera. camera.set( cv2.CAP_PROP_FRAME_WIDTH, 620 ) camera.set( cv2.CAP_PROP_FRAME_HEIGHT, 480 )

For example,

camera.set( cv2.CAP_PROP_FRAME_WIDTH, 800 ) camera.set( cv2.CAP_PROP_FRAME_HEIGHT, 600 ) camera.set( cv2.CAP_PROP_FRAME_WIDTH, 1024 ) camera.set( cv2.CAP_PROP_FRAME_HEIGHT, 768 ) camera.set( cv2.CAP_PROP_FRAME_WIDTH, 1600 ) camera.set( cv2.CAP_PROP_FRAME_HEIGHT, 1200 )

How is the frame rate supported?

camera.set(cv2.CAP_PROP_FPS, 30) #<--- Add line. camera.set(cv2.CAP_PROP_FRAME_WIDTH, 620) camera.set(cv2.CAP_PROP_FRAME_HEIGHT, 480)

Or how is the compliance status of USB 2.0 / USB 3.0?

[idata]

Hi Pinto

Many thanks.

I have now got the live-image-picam experiment to work.

When I use live-image-classifier and your 3 lines

camera.set(cv2.CAP_PROP_FPS, 30) #<--- Add line.

camera.set(cv2.CAP_PROP_FRAME_WIDTH, 620) camera.set(cv2.CAP_PROP_FRAME_HEIGHT, 480)

I get two windows the one with predictions and then the camera view that is pink……

sojohan

[idata]

my webcam is the cheapest Trust with resolution 640 * 480 and supports usb 2.0.

Soren

[idata]

Hi again

I got a new webcam 1280*720 when I use these settings and the above commands my raspberry begins to reboot? Just before the reboot I do see a black ncs inference window….

Sojohan