Mary-Ann's profile - activity

Did anybody find a solution? I have currently the same problem :(

Hi, were you able to solve this problem? I have currently the same issue :(

Hi, your numpy version is probably not up to date. I had the same error message and a simple update solved the problem!

Running DNN on GPU (Problems with OpenCL and Halide) Hi, I am running a Caffe based network, called DetectNet (https://

Hi,

I would like to check, if a given point is inside or outside of a given shape. I have already found the pointPolygonTest() function for this purpose. But my problem is, that I only have the corners of the shape, and I know that the edges are straight. Is there a way to create contours[] straight form the corner points? The only solution I found is to render (write into Mat) the edges and detect the shape to get the contours. But I actually dont need the rendered shape, I only want to perform this test. So I would like to skip this step if possible...

Thank you for any answers! Mary-Ann

Right, only the corners are enough for the algorithm. You dont need every single contour point. But if somebody needs it

Hi! I thought that neighboring elements of the contour vector need to be connected pixels on the image (just like this a

Create contour from corner points Hi, I would like to check, if a given point is inside or outside of a given shape. I

@dkurt your answer is correct and the application is finally running! I only needed to import math too. Thank you for yo

Hi,

I would like to use the OpenCV DNN framework with a custom trained Caffe network. I am using the newest OpenCV Version and contrib libs, I compiled two weeks ago, I guess. I have already checked the dnn samples, and with the precompiled SqueezeDet and SqueezeNet examples everything works just fine. But if I load my network I get the following exception:

OpenCV(3.4.1-dev) Error: Unspecified error (Can't create layer "cluster" of type "Python") in getLayerInstance, file opencv-master/modules/dnn/src/dnn.cpp, line 388 terminate called after throwing an instance of 'cv::Exception' what(): OpenCV(3.4.1-dev) opencv-master/modules/dnn/src/dnn.cpp:388: error: (-2) Unspecified error: Can't create layer "cluster" of type "Python" in function getLayerInstance

The network should be fine, I have tested it outside the OpenCV framework. The caffe version is 0.15.14, digits version is 5.1-dev. I use OpenCV in C++ not in Python, could it be the error?

Thanks a lot for any answers! Mary

EDIT: Here is the last layer of the prototxt, that probably causes the problem:

layer {    
  name: "cluster"    
  type: "Python"    
  bottom: "coverage"    
  bottom: "bboxes"    
  top: "bbox-list"    
  python_param {    
    module: "caffe.layers.detectnet.clustering"    
    layer: "ClusterDetections"    
    param_str: "1248, 352, 16, 0.6, 3, 0.02, 22, 1"    
  }    
}

Hi, I switched to Python to test the application, but I still get some error. I was following this tutorial: https://www

Hi, I switched to Python to test the application, but I still get some error. I was following this tutorial: https://www

How to use BING Objectness with self trained model? Hi, I would like to use the BING Objectness feature with a custom t

This is actually the answer of @berak, but their post disappeared... One should only convert the .wS1 (etc) model files

I will post it then, it can be helpful for someone else too.

Please post your answer again, it was correct and solved my problem!

It worked, thank you! :D

Hi, I would like to use the BING Objectness feature with a custom trained model. I am aware, that it is not possible inside of OpenCV, that is why I downloaded the Linux BING Objectness code (https://github.com/torrvision/Objectness) and trained the algorithm by myself. If the training is done, the code creates the following files:

• Filter.png
• ObjNessB2W8MAXBGR.idx
• ObjNessB2W8MAXBGR.wS1
• ObjNessB2W8MAXBGR.wS2
• ObjNessB2W8MAXBGR.xN
• ObjNessB2W8MAXBGR.xP
• PerImgAll.m
• PosNeg.m
• PosNeg.png

and the proposed windows for the test data are also generated in an additional folder "BBoxesB2W8MAXBGR" . I thought I only need to set the training path to the newly generated model files but I get an error:

Can't load model: /ObjNessB2W8MAXBGR.wS1 or /ObjNessB2W8MAXBGR.idx
Can't load model: /ObjNessB2W8HSV.wS1 or /ObjNessB2W8HSV.idx
Can't load model: /ObjNessB2W8I.wS1 or /ObjNessB2W8I.idx

Since the original code managed to create the object proposals I assume, that the model files were generated correctly. But why is OpenCV not able to read them?

Thanks a lot for any help! Mary C:\fakepath\ObjNessB2W8MAXBGR.wS1.png

How to use BING Objectness with self trained model? Hi, I would like to use the BING Objectness feature with a custom t

How to use BING Objectness with self trained model? Hi, I would like to use the BING Objectness feature with a custom t

How to use BING Objectness with self trained model? Hi, I would like to use the BING Objectness feature with a custom t

Yes, I want to use ObjectnessBing from Saliency

How to use BING Objectness with self trained model? Hi, I would like to use the BING Objectness feature with a custom t

Hi, does it mean, that it is not possible currently to solve this problem inside my C++ framework? Unfortunately I am st

Take a look at this thread: https://github.com/opencv/opencv/issues/8097 , it solved the problem my similar me. Basicall

Hi, I updated my OpenCV but I still get the error message saying: OpenCV(3.4.1-dev) Error: Unspecified error (Can't cr

I updated the question so that only the last layer can be seen. The network was trained using DIGITS (https://github.com

Assertion Error with Custom Trained Caffe Hi, I would like to use the OpenCV DNN framework with a custom trained Caffe

Hi, I updated the question, I hope it helps to solve my problem

Assertion Error with Custom Trained Caffe Hi, I would like to use the OpenCV DNN framework with a custom trained Caffe

Hi, I'm not sure that I get your question right, but here is how I use my network in my application: ReadNetFromCaffe(pr

Assertion Error with Custom Trained Caffe Hi, I would like to use the OpenCV DNN framework with a custom trained Caffe

You were right! The training failed, I used in the training data path backslashes instead of normal slashes. Everything works just fine now. Thank you for your comments!

Yes, unfortunately it still fails, and I get the same message :/

Hi everyone,

I would like to calculate the BING objectness of some images, but I can not get my code to run. I am using the example code, released here: https://gist.github.com/thorikawa/fea... but if I call computeSaliency() I get an assertion error:

OpenCV Error: Assertion failed (w1f.cols * w1f.rows == D && w1f.type() == CV_32F && w1f.isContinuous()) in cv::saliency::ObjectnessBING::FilterTIG::update, file \opencv_contrib-master\opencv_contrib-master\modules\saliency\src\BING\FilterTIG.cpp, line 74

I could imagine, that maybe the training fails, even though I set the training data path just like the example says. How could I check, that the training went well? Or does anyone have any idea, how I could get rid of this assertion error?

Thanks a lot for the help!