Cannot use the openvino's pre built opencv

[ghost]

Hello. I am trying to use open vino's version of opencv which is already build with IE backend but i am unable to do so. Whenever i try to load .xml and .bin files of the model in the cv.dnn.readNet , i get the following error:

Traceback (most recent call last):
File "facedetection.py", line 16, in
'pruned_mobilenet_reduced_ssd_shared_weights/dldt/face-detection-adas-0001.xml')
cv2.error: OpenCV(4.0.0) /io/opencv/modules/dnn/src/dnn.cpp:2538: error: (-2:Unspecified error) Build OpenCV with Inference Engine to enable loading models from Model Optimizer. in function 'readFromModelOptimizer

The installation guide says to source the /opt/intel/openvino_2019.1.094/bin/setupvars.sh script in order to update the $OpenCV_DIR variable which I did but it didnt work. When i echo the variable, it points to the following path:

/opt/intel/openvino_2019.1.094/opencv/cmake

I even tried to sym link the cv2.so file from /opt/intel/openvino_2019.1.094/python/python3.5/ directory to the /usr/local/lib/python3.5/dist-packages/ directory but still it doesnt work.
Can you'll please enlist the exact steps to be taken or where i am going wrong? Thanks in advance.

[snosov1]

@dkurt, any ideas?

[dkurt]

@sovereignscout, Please show the output of the following python commands from your script:

import cv2 as cv
print(cv.__file__)

[farshadopencv]

Hi. I get same error when I use bin and xml files in readFromModelOptimizer function in openvino's version of opencv built in openvino.

I also build opencv 4.0.0-openvino and opencv 4.1.0 with
-DWITH_INF_ENGINE=ON -DENABLE_CXX11=ON
to use IE backend and it build successfully, but again I got error
Build OpenCV with Inference Engine to enable loading models from Model Optimizer. in function 'readFromModelOptimizer, when I use bin and xml files in readFromModelOptimizer function

[alalek]

CMake output should contain these lines:

-- Detected InferenceEngine: cmake package
...
--     Inference Engine:            YES (2019010000 / 1.6.0)
--                 libs:            /opt/intel/openvino_2019.1.094/deployment_tools/inference_engine/lib/intel64/libinference_engine.so
--             includes:            /opt/intel/openvino_2019.1.094/deployment_tools/inference_engine/include

4.0.0
4.0.0-openvino

These OpenCV versions are not able to work properly with IE from OpenVINO 2019R1.
You should use OpenCV 4.1.0 / 4.1.0-openvino / master.

[dkurt]

@farshadopencv, Please analyze the CMake summary. It contains all the information about your build: getBuildInformation

[farshadopencv]

@alalek @dkurt Thanks for your help. Now I can build opencv 4.1.0 with IE backend. But now I encounter another problem. when I pass my bin, xml files of model into object_detection.cpp script, I have following error:

OpenCV(4.1.0) Error: Assertion failed (> Failed to initialize Inference Engine backend: Unsupported primitive of type: PriorBoxClustered name: PriorBoxClustered_5
..\src\mkldnn_plugin\mkldnn_node.cpp:167
c:\program files (x86)\intelswtools\openvino_2019.1.087\deployment_tools\inference_engine\include\details/ie_exception_conversion.hpp:71
) in cv::dnn::InfEngineBackendNet::initPlugin, file C:\o\opencv\modules\dnn\src\op_inf_engine.cpp, line 813

I changed object_detection.cpp to avoid parser as follows:

**#define _CRT_SECURE_NO_WARNINGS

#include
#include

#include <opencv2/dnn.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>

#include "common.hpp"

std::string keys =
"{ help h | | Print help message. }"
"{ @alias | | An alias name of model to extract preprocessing parameters from models.yml file. }"
"{ zoo | models.yml | An optional path to file with preprocessing parameters }"
"{ device | 0 | camera device number. }"
"{ input i | | Path to input image or video file. Skip this argument to capture frames from a camera. }"
"{ framework f | | Optional name of an origin framework of the model. Detect it automatically if it does not set. }"
"{ classes | | Optional path to a text file with names of classes to label detected objects. }"
"{ thr | .5 | Confidence threshold. }"
"{ nms | .4 | Non-maximum suppression threshold. }"
"{ backend | 0 | Choose one of computation backends: "
"0: automatically (by default), "
"1: Halide language (http://halide-lang.org/), "
"2: Intel's Deep Learning Inference Engine (https://software.intel.com/openvino-toolkit), "
"3: OpenCV implementation }"
"{ target | 0 | Choose one of target computation devices: "
"0: CPU target (by default), "
"1: OpenCL, "
"2: OpenCL fp16 (half-float precision), "
"3: VPU }";

using namespace cv;
using namespace dnn;

float confThreshold, nmsThreshold;
std::vectorstd::string classes;

void postprocess(Mat& frame, const std::vector& out, Net& net);

void drawPred(int classId, float conf, int left, int top, int right, int bottom, Mat& frame);

void callback(int pos, void* userdata);

std::vector getOutputsNames(const Net& net);

int main(int argc, char** argv)
{

confThreshold = 0.6f;
nmsThreshold = .4f;
float scale = 0.00784f;
Scalar mean = Scalar(127.5, 127.5, 127.5);
bool swapRB = true;
int inpWidth = 300;
int inpHeight = 300;

int backend = 2;
int target = 0;



std::string modelPath = "E:\carPlateSsdlite.bin";
std::string configPath = "E:\carPlateSsdlite.xml";




Net net = readNet(modelPath, configPath);
net.setPreferableBackend(backend);
net.setPreferableTarget(target);
std::vector<String> outNames = net.getUnconnectedOutLayersNames();


static const std::string kWinName = "Deep learning object detection in OpenCV";
namedWindow(kWinName, WINDOW_NORMAL);
int initialConf = (int)(confThreshold * 100);
createTrackbar("Confidence threshold, %", kWinName, &initialConf, 99, callback);



Mat  blob;
Mat frame = imread("E:\img25.jpg", 1);
while (waitKey(1) < 0)
{
	
	if (frame.empty())
	{
		waitKey();
		break;
	}

	
	Size inpSize(inpWidth > 0 ? inpWidth : frame.cols,
		inpHeight > 0 ? inpHeight : frame.rows);
	blobFromImage(frame, blob, scale, inpSize, mean, swapRB, false);

	
	net.setInput(blob);
	if (net.getLayer(0)->outputNameToIndex("im_info") != -1)  // Faster-RCNN or R-FCN
	{
		resize(frame, frame, inpSize);
		Mat imInfo = (Mat_<float>(1, 3) << inpSize.height, inpSize.width, 1.6f);
		net.setInput(imInfo, "im_info");
	}
	std::vector<Mat> outs;
	net.forward(outs, outNames);

	postprocess(frame, outs, net);

	
	std::vector<double> layersTimes;
	double freq = getTickFrequency() / 1000;
	double t = net.getPerfProfile(layersTimes) / freq;
	std::string label = format("Inference time: %.2f ms", t);
	putText(frame, label, Point(0, 15), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 255, 0));

	imshow(kWinName, frame);
}
return 0;

}

void postprocess(Mat& frame, const std::vector& outs, Net& net)
{
static std::vector outLayers = net.getUnconnectedOutLayers();
static std::string outLayerType = net.getLayer(outLayers[0])->type;

std::vector<int> classIds;
std::vector<float> confidences;
std::vector<Rect> boxes;
if (outLayerType == "DetectionOutput")
{
	
	CV_Assert(outs.size() > 0);
	for (size_t k = 0; k < outs.size(); k++)
	{
		float* data = (float*)outs[k].data;
		for (size_t i = 0; i < outs[k].total(); i += 7)
		{
			float confidence = data[i + 2];
			if (confidence > confThreshold)
			{
				int left = (int)data[i + 3];
				int top = (int)data[i + 4];
				int right = (int)data[i + 5];
				int bottom = (int)data[i + 6];
				int width = right - left + 1;
				int height = bottom - top + 1;
				if (width * height <= 1)
				{
					left = (int)(data[i + 3] * frame.cols);
					top = (int)(data[i + 4] * frame.rows);
					right = (int)(data[i + 5] * frame.cols);
					bottom = (int)(data[i + 6] * frame.rows);
					width = right - left + 1;
					height = bottom - top + 1;
				}
				classIds.push_back((int)(data[i + 1]) - 1);  // Skip 0th background class id.
				boxes.push_back(Rect(left, top, width, height));
				confidences.push_back(confidence);
			}
		}
	}
}
else if (outLayerType == "Region")
{
	for (size_t i = 0; i < outs.size(); ++i)
	{
		
		float* data = (float*)outs[i].data;
		for (int j = 0; j < outs[i].rows; ++j, data += outs[i].cols)
		{
			Mat scores = outs[i].row(j).colRange(5, outs[i].cols);
			Point classIdPoint;
			double confidence;
			minMaxLoc(scores, 0, &confidence, 0, &classIdPoint);
			if (confidence > confThreshold)
			{
				int centerX = (int)(data[0] * frame.cols);
				int centerY = (int)(data[1] * frame.rows);
				int width = (int)(data[2] * frame.cols);
				int height = (int)(data[3] * frame.rows);
				int left = centerX - width / 2;
				int top = centerY - height / 2;

				classIds.push_back(classIdPoint.x);
				confidences.push_back((float)confidence);
				boxes.push_back(Rect(left, top, width, height));
			}
		}
	}
}
else
	CV_Error(Error::StsNotImplemented, "Unknown output layer type: " + outLayerType);

std::vector<int> indices;
NMSBoxes(boxes, confidences, confThreshold, nmsThreshold, indices);
for (size_t i = 0; i < indices.size(); ++i)
{
	int idx = indices[i];
	Rect box = boxes[idx];
	drawPred(classIds[idx], confidences[idx], box.x, box.y,
		box.x + box.width, box.y + box.height, frame);
}

}

void drawPred(int classId, float conf, int left, int top, int right, int bottom, Mat& frame)
{
rectangle(frame, Point(left, top), Point(right, bottom), Scalar(0, 255, 0));

std::string label = format("%.2f", conf);
if (!classes.empty())
{
	CV_Assert(classId < (int)classes.size());
	label = classes[classId] + ": " + label;
}

int baseLine;
Size labelSize = getTextSize(label, FONT_HERSHEY_SIMPLEX, 0.5, 1, &baseLine);

top = max(top, labelSize.height);
rectangle(frame, Point(left, top - labelSize.height),
	Point(left + labelSize.width, top + baseLine), Scalar::all(255), FILLED);
putText(frame, label, Point(left, top), FONT_HERSHEY_SIMPLEX, 0.5, Scalar());

}

void callback(int pos, void*)
{
confThreshold = pos * 0.01f;
}**

[dkurt]

OpenCV(4.1.0) Error: Assertion failed (> Failed to initialize Inference Engine backend: Unsupported primitive of type: PriorBoxClustered name: PriorBoxClustered_5
..\src\mkldnn_plugin\mkldnn_node.cpp:167
c:\program files (x86)\intelswtools\openvino_2019.1.087\deployment_tools\inference_engine\include\details/ie_exception_conversion.hpp:71
) in cv::dnn::InfEngineBackendNet::initPlugin, file C:\o\opencv\modules\dnn\src\op_inf_engine.cpp, line 813

Similar issue: opencv/opencv#14409. It looks like there is something wrong with Windows package.

@farshadopencv please check the solution from opencv/opencv#14409 (comment). It looks like your CPU might also don't support AVX2.

[cuixing158]

@farshadopencv thank you give a example!!! I ran successfully on "Release" mode

[dongyangli-del]

Hello, When I input the command " sudo python3 face_detection.py", it tells me that : Traceback (most recent call last):
File "face_detection.py", line 3, in
net = cv.dnn.readNet('face-detection-adas-0001.xml', 'face-detection-adas-0001.bin')
cv2.error: OpenCV(3.4.3) /home/pi/opencv-python/opencv/modules/dnn/src/dnn.cpp:2365: error: (-2:Unspecified error) Build OpenCV with Inference Engine to enable loading models from Model Optimizer. in function 'readFromModelOptimizer'

Have you ever come across a problem like this? Any good Suggestions? thank you!

[alalek]

3.4.3

This means that used OpenCV binaries are not from OpenVINO package (-openvino suffix is expected in version identifier).
Check cv.__file__ and cv.getBuildInformation() to confirm that.

sudo

Don't use sudo. At least it drops environment variables (due to security reasons).

[Welyweloo]

Hello @alalek,
I've been trying to understand your previous message.
Where should I add that -openvino suffix please? I am having the same issue.

(cv) aurelie@aurelie-VirtualBox:~/LO_Computervision_YOLO$ python object_detection_caffe.py --input IMG_4587.MOV --output ./
/home/aurelie/.virtualenvs/cv/lib/python3.8/site-packages/cv2/cv2.cpython-38-x86_64-linux-gnu.so

General configuration for OpenCV 4.5.1 =====================================
  Version control:               4.5.1-dirty

  Platform:
    Timestamp:                   2021-01-02T13:00:02Z
    Host:                        Linux 4.15.0-1077-gcp x86_64
    CMake:                       3.18.4
    CMake generator:             Unix Makefiles
    CMake build tool:            /bin/gmake
    Configuration:               Release

  CPU/HW features:
    Baseline:                    SSE SSE2 SSE3
      requested:                 SSE3
    Dispatched code generation:  SSE4_1 SSE4_2 FP16 AVX AVX2 AVX512_SKX
      requested:                 SSE4_1 SSE4_2 AVX FP16 AVX2 AVX512_SKX
      SSE4_1 (15 files):         + SSSE3 SSE4_1
      SSE4_2 (1 files):          + SSSE3 SSE4_1 POPCNT SSE4_2
      FP16 (0 files):            + SSSE3 SSE4_1 POPCNT SSE4_2 FP16 AVX
      AVX (4 files):             + SSSE3 SSE4_1 POPCNT SSE4_2 AVX
      AVX2 (29 files):           + SSSE3 SSE4_1 POPCNT SSE4_2 FP16 FMA3 AVX AVX2
      AVX512_SKX (4 files):      + SSSE3 SSE4_1 POPCNT SSE4_2 FP16 FMA3 AVX AVX2 AVX_512F AVX512_COMMON AVX512_SKX

  C/C++:
    Built as dynamic libs?:      NO
    C++ standard:                11
    C++ Compiler:                /usr/lib/ccache/compilers/c++  (ver 9.3.1)
    C++ flags (Release):         -Wl,-strip-all   -fsigned-char -W -Wall -Werror=return-type -Werror=non-virtual-dtor -Werror=address -Werror=sequence-point -Wformat -Werror=format-security -Wmissing-declarations -Wundef -Winit-self -Wpointer-arith -Wshadow -Wsign-promo -Wuninitialized -Wsuggest-override -Wno-delete-non-virtual-dtor -Wno-comment -Wimplicit-fallthrough=3 -Wno-strict-overflow -fdiagnostics-show-option -Wno-long-long -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections  -msse -msse2 -msse3 -fvisibility=hidden -fvisibility-inlines-hidden -O3 -DNDEBUG  -DNDEBUG
    C++ flags (Debug):           -Wl,-strip-all   -fsigned-char -W -Wall -Werror=return-type -Werror=non-virtual-dtor -Werror=address -Werror=sequence-point -Wformat -Werror=format-security -Wmissing-declarations -Wundef -Winit-self -Wpointer-arith -Wshadow -Wsign-promo -Wuninitialized -Wsuggest-override -Wno-delete-non-virtual-dtor -Wno-comment -Wimplicit-fallthrough=3 -Wno-strict-overflow -fdiagnostics-show-option -Wno-long-long -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections  -msse -msse2 -msse3 -fvisibility=hidden -fvisibility-inlines-hidden -g  -O0 -DDEBUG -D_DEBUG
    C Compiler:                  /usr/lib/ccache/compilers/cc
    C flags (Release):           -Wl,-strip-all   -fsigned-char -W -Wall -Werror=return-type -Werror=non-virtual-dtor -Werror=address -Werror=sequence-point -Wformat -Werror=format-security -Wmissing-declarations -Wmissing-prototypes -Wstrict-prototypes -Wundef -Winit-self -Wpointer-arith -Wshadow -Wuninitialized -Wno-comment -Wno-strict-overflow -fdiagnostics-show-option -Wno-long-long -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections  -msse -msse2 -msse3 -fvisibility=hidden -O3 -DNDEBUG  -DNDEBUG
    C flags (Debug):             -Wl,-strip-all   -fsigned-char -W -Wall -Werror=return-type -Werror=non-virtual-dtor -Werror=address -Werror=sequence-point -Wformat -Werror=format-security -Wmissing-declarations -Wmissing-prototypes -Wstrict-prototypes -Wundef -Winit-self -Wpointer-arith -Wshadow -Wuninitialized -Wno-comment -Wno-strict-overflow -fdiagnostics-show-option -Wno-long-long -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections  -msse -msse2 -msse3 -fvisibility=hidden -g  -O0 -DDEBUG -D_DEBUG
    Linker flags (Release):      -Wl,--exclude-libs,libippicv.a -Wl,--exclude-libs,libippiw.a -L/root/ffmpeg_build/lib  -Wl,--gc-sections -Wl,--as-needed  
    Linker flags (Debug):        -Wl,--exclude-libs,libippicv.a -Wl,--exclude-libs,libippiw.a -L/root/ffmpeg_build/lib  -Wl,--gc-sections -Wl,--as-needed  
    ccache:                      YES
    Precompiled headers:         NO
    Extra dependencies:          ade Qt5::Core Qt5::Gui Qt5::Widgets Qt5::Test Qt5::Concurrent /lib64/libpng.so /lib64/libz.so dl m pthread rt
    3rdparty dependencies:       ittnotify libprotobuf libjpeg-turbo libwebp libtiff libopenjp2 IlmImf quirc ippiw ippicv

  OpenCV modules:
    To be built:                 calib3d core dnn features2d flann gapi highgui imgcodecs imgproc ml objdetect photo python3 stitching video videoio
    Disabled:                    world
    Disabled by dependency:      -
    Unavailable:                 java python2 ts
    Applications:                -
    Documentation:               NO
    Non-free algorithms:         NO

  GUI: 
    QT:                          YES (ver 5.15.0)
      QT OpenGL support:         NO
    GTK+:                        NO
    VTK support:                 NO

  Media I/O: 
    ZLib:                        /lib64/libz.so (ver 1.2.7)
    JPEG:                        libjpeg-turbo (ver 2.0.6-62)
    WEBP:                        build (ver encoder: 0x020f)
    PNG:                         /lib64/libpng.so (ver 1.5.13)
    TIFF:                        build (ver 42 - 4.0.10)
    JPEG 2000:                   build (ver 2.3.1)
    OpenEXR:                     build (ver 2.3.0)
    HDR:                         YES
    SUNRASTER:                   YES
    PXM:                         YES
    PFM:                         YES

  Video I/O:
    DC1394:                      NO
    FFMPEG:                      YES
      avcodec:                   YES (58.109.100)
      avformat:                  YES (58.61.100)
      avutil:                    YES (56.60.100)
      swscale:                   YES (5.8.100)
      avresample:                NO
    GStreamer:                   NO
    v4l/v4l2:                    YES (linux/videodev2.h)

  Parallel framework:            pthreads

  Trace:                         YES (with Intel ITT)

  Other third-party libraries:
    Intel IPP:                   2020.0.0 Gold [2020.0.0]
           at:                   /tmp/pip-req-build-ms668fyv/_skbuild/linux-x86_64-3.8/cmake-build/3rdparty/ippicv/ippicv_lnx/icv
    Intel IPP IW:                sources (2020.0.0)
              at:                /tmp/pip-req-build-ms668fyv/_skbuild/linux-x86_64-3.8/cmake-build/3rdparty/ippicv/ippicv_lnx/iw
    Lapack:                      NO
    Eigen:                       NO
    Custom HAL:                  NO
    Protobuf:                    build (3.5.1)

  OpenCL:                        YES (no extra features)
    Include path:                /tmp/pip-req-build-ms668fyv/opencv/3rdparty/include/opencl/1.2
    Link libraries:              Dynamic load

  Python 3:
    Interpreter:                 /opt/python/cp38-cp38/bin/python (ver 3.8.6)
    Libraries:                   libpython3.8.a (ver 3.8.6)
    numpy:                       /tmp/pip-build-env-qm375ina/overlay/lib/python3.8/site-packages/numpy/core/include (ver 1.17.3)
    install path:                python

  Python (for build):            /bin/python2.7

  Java:                          
    ant:                         NO
    JNI:                         NO
    Java wrappers:               NO
    Java tests:                  NO

  Install to:                    /tmp/pip-req-build-ms668fyv/_skbuild/linux-x86_64-3.8/cmake-install
-----------------------------------------------------------------


Initializing...
Traceback (most recent call last):
  File "object_detection_caffe.py", line 199, in <module>
    net = cv2.dnn.readNet('/open_model_zoo-master/tools/downloader/intel/vehicle-attributes-recognition-barrier-0039/FP32/vehicle-attributes-recognition-barrier-0039.bin', 
cv2.error: OpenCV(4.5.1) /tmp/pip-req-build-ms668fyv/opencv/modules/dnn/src/dnn.cpp:3901: error: (-2:Unspecified error) Build OpenCV with Inference Engine to enable loading models from Model Optimizer. in function 'readFromModelOptimizer'

[shahla-ai]

hi @farshadopencv , I wish you can help me
can you tell me how you compiled OpenCV with openvino IE backend from source ?
all documentations show how to use openvino's OpenCV , but that is not what I want
best regards

[dkurt]

@shahla-ai, https://github.com/opencv/opencv/wiki/Intel%27s-Deep-Learning-Inference-Engine-backend#build-opencv-from-source

[ZhongQiyu]

3.4.3

This means that used OpenCV binaries are not from OpenVINO package (-openvino suffix is expected in version identifier). Check cv.__file__ and cv.getBuildInformation() to confirm that.

sudo

Don't use sudo. At least it drops environment variables (due to security reasons).
@alalek I was trying to figure out the information generated from cv.getBuildInformation(), and for the point I am getting myself around with the version information:
General configuration for OpenCV 4.5.5 =====================================
Version control: 4.5.5
Is this expected to be adding a suffix of -openvino?