Intel® Distribution of OpenVINO™ Toolkit
Community assistance about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all aspects of computer vision-related on Intel® platforms.

Raspbian* OS [ ERROR ] AssertionFailed: inputs.size() == 1

MIfil
Beginner
719 Views

Going through the Install OpenVINO™ toolkit for Raspbian* OS demo, but running into this error when trying to build the Object Detection Sample. Trying to use a stock photo saved in my downloads. Can someone help me solve this error? Also if anyone can tell me how to set an input for a USB webcam as well it would be greatly appreciated.

pi@raspberrypi:~/Downloads/build $ ./armv7l/Release/object_detection_sample_ssd -m face-detection-adas-0001.xml -d MYRIAD -i /home/pi/Documents/download.jpeg
[ INFO ] InferenceEngine: 
API version ............ 1.4
Build .................. 19154
Parsing input parameters
[ INFO ] Files were added: 1
[ INFO ]   /home/pi/Documents/download.jpeg
[ INFO ] Loading plugin

API version ............ 1.5
Build .................. 19154
Description ....... myriadPlugin
[ INFO ] Loading network files:
face-detection-adas-0001.xml
face-detection-adas-0001.bin
[ INFO ] Preparing input blobs
[ INFO ] Batch size is 1
[ INFO ] Preparing output blobs
[ INFO ] Loading model to the plugin
[ ERROR ] AssertionFailed: inputs.size() == 1

 

0 Kudos
7 Replies
Shubha_R_Intel
Employee
719 Views

Dear Ifill, Marcus,

Can you kindly try object_detection_sample instead of object_detection_sample_ssd ?

Let me know the results here.

Thanks for your patience,

Shubha

 

0 Kudos
MIfil
Beginner
719 Views
Thanks for your response. I do not see a folder for object_detection_sample in my build files, only the object_detection_sample_ssd. This is what happened:

pi@raspberrypi:~/Downloads/build $ make -j2 object_detection_sample
make: *** No rule to make target 'object_detection_sample'.  Stop.
I saw there was the object_detection_demo along with the ssd version so, I tried that and got this error:

pi@raspberrypi:~/Downloads/build $ make -j2 object_detection_demo
[ 12%] Built target format_reader
[ 83%] Built target ie_cpu_extension
[ 95%] Built target gflags_nothreads_static
Scanning dependencies of target object_detection_demo
[ 95%] Building CXX object object_detection_demo/CMakeFiles/object_detection_demo.dir/main.cpp.o
[100%] Linking CXX executable ../armv7l/Release/object_detection_demo
[100%] Built target object_detection_demo
pi@raspberrypi:~/Downloads/build $ ./armv7l/Release/object_detection_demo -m face-detection-adas-0001.xml -d MYRIAD -i /home/pi/Documents/download.jpeg
[ INFO ] InferenceEngine: 
	API version ............ 1.4
	Build .................. 19154
Parsing input parameters
[ INFO ] Files were added: 1
[ INFO ]     /home/pi/Documents/download.jpeg
[ INFO ] Loading plugin

	API version ............ 1.5
	Build .................. 19154
	Description ....... myriadPlugin
[ INFO ] Loading network files:
	face-detection-adas-0001.xml
	face-detection-adas-0001.bin
[ ERROR ] Can't find output layer named bbox_pred

I also tried running the yolo3 demo with my webcam and got the error:

pi@raspberrypi:~/Downloads/build $ ./armv7l/Release/object_detection_demo_yolov3_async -m face-detection-adas-0001.xml -d MYRIAD -i cam
InferenceEngine: 
	API version ............ 1.4
	Build .................. 19154
[ INFO ] Parsing input parameters
[ INFO ] Reading input
[ INFO ] Loading plugin

	API version ............ 1.5
	Build .................. 19154
	Description ....... myriadPlugin
[ INFO ] Loading network files
[ INFO ] Batch size is forced to  1.
[ INFO ] Checking that the inputs are as the demo expects
[ INFO ] Checking that the outputs are as the demo expects
[ ERROR ] This demo only accepts networks with three layers

 

0 Kudos
Shubha_R_Intel
Employee
719 Views

Dear fill, Marcus

I'm very sorry but I instructed you improperly before. Please see The OpenVino Samples Matrix Mapping . As you can see for IR face-detection-adas-0001 you should use the interactive_face_detection_demo . Very sorry that I misled you in my previous suggestions.

Hopefully everything will work fine for you now.

Thanks,

Shubha

0 Kudos
MIfil
Beginner
719 Views

Shubha,

Tried using the interactive_face_detection_demo, but my system keeps freezing when I use the make -j2 command with it. I have not had any problems using this command with any of the other pre trained models. Is there a workaround for this?

0 Kudos
Shubha_R_Intel
Employee
719 Views

Dear Ifill, Marcus,

hmmmm that's strange. How about just try make ? 

Let me know what happens,

Thanks,

Shubha

 

0 Kudos
MIfil
Beginner
719 Views

make interactive_face_detection_demo worked, but when I try to run the demo, I get the same Assertion Error I was getting initially. 

pi@raspberrypi:~/Downloads/build $ ./armv7l/Release/interactive_face_detection_demo -m face-detection-adas-0001.xml -d MYRIAD -i /home/pi/Documents/download.jpeg
InferenceEngine: 
	API version ............ 1.4
	Build .................. 19154
[ INFO ] Parsing input parameters
[ INFO ] Reading input
[ INFO ] Loading plugin MYRIAD

	API version ............ 1.5
	Build .................. 19154
	Description ....... myriadPlugin
[ INFO ] Loading network files for Face Detection
[ INFO ] Batch size is set to 1
[ INFO ] Checking Face Detection network inputs
[ INFO ] Checking Face Detection network outputs
[ INFO ] Loading Face Detection model to the MYRIAD plugin
[ ERROR ] AssertionFailed: inputs.size() == 1

 

0 Kudos
Shubha_R_Intel
Employee
719 Views

Dear Ifill, Marcus,

People on this community have gotten OpenVino working with USB Cameras. But for OpenCV questions you should post your issues to https://answers.opencv.org/questions/ (how to get OpenCV to open usb cameras)

Are you sure that you followed The Online Interactive Face Demo Doc carefully ?

And did you run setupvars.sh first from the same command shell where you ran the demo ?

Thanks,

Shubha

0 Kudos
Reply