aguila's profile - activity

Hello, i succesfully linked opencv to my android c++ native app.. now I encountered a problem where i cannot read my models (ex. YOLO) I pasted them here: /storage/emulated/0/DCIM/ <model> but when running I see that the models cannot be found/read. The tutorial on the opencv page is for java implementation, I would like to implement something similar but using native C++.

What I have tried:

• set permissions on my app to READ/WRITE: <uses-permission android:name="android.permission.READ_EXTERNAL_STORAGE"/>
• similar approach than: question opencv answers

Has someone encountered the same issue? Or has some tips? Thaaaanks!

Oh okay I managed to solve it, I will post the solution in case that helps someone. If you do not have your device "root

Android dnn in native C++ Hello, i succesfully linked opencv to my android c++ native app.. now I encountered a problem

Hallo Tilman, have you tried installing it through pip? i have it like that on my environment -> pip install opencv-p

thank you for the answer! okay i will update to the latest release..

hello! i am havind a problem with the imshow function, according to the documentation it supports Mat of different types than CV_8U imshow_doc, i have been using it on other opencv versions and it works (example opencv 3.4.1).. The Mat that i want to show is CV_64F type, i tried also with CV_16U but i get the same assertion error, i checked the source file:

OpenCV(4.0.0) c:\build\master_winpack-build-win64-vc15\opencv\modules\highgui\src\window_w32.cpp:1230: error: (-215:Assertion failed) dst.data == (uchar*)dst_ptr in function 'cvShowImage'

and my temporary solution would be to comment that assertion but i am not sure if that would bring other problems. I see in the assertion that it is expecting a uchar data.. maybe thats why it gets error with other types?? Has someone experienced something similar? or has any ideas?

thanks!

imshow data types? hello! i am havind a problem with the imshow function, according to the documentation it supports Mat

hello @MedoCV i was playing around and trying to implement something similar.. i get also some issues when i start rotat

hello @MedoCV i was playing around and trying to implement something similar.. i get also some issues when i start rotat

Hello, i forgot to finish this example.. thanks for the hints @dkurt . I just made the modifications to the network. The

ok i will try it later today and post my results here.. thanks!

Hello @dkurt thank you for your help, sorry i did not checked in the past week the two different layers. I am looking no

Hello @dkurt thank you for your help, sorry i did not checked in the past week the two different layers. I am looking no

Hello, i am porting an algorithm to opencv https://arxiv.org/pdf/1804.06039.pdf , the models are available here: https://github.com/Jack-CV/PCN-FaceDe... . I finished the first stage and while implementing the second, the outputs of the network are a bit weird:

Input Data: I: 1 C: 3 H: 24 W: 24

Scores Data: I: 1 C: 2 H: 299777088 W: 1

Regression Data: I: 1 C: 3 H: 309665792 W: 1

Rotate Data: I: 1 C: 3 H: 299780800 W: 1

The channels size of each output is correct, but the H,W are confusing me. I don't know if this has to be with the case that the model is the same for all the three networks?. Or maybe is an overflow issue? I tested it just forwarding a simple image with the secont network "PCN-2.prototxt" the output is similar.. has someone experienced something like this?

thanks!

solved... the error was accessing bad dimensions of blob

Hi @berak, the prebuilt model i downloaded from the repo https://wywu.github.io/projects/LAB/support/WFLW_final.tar.gz a

dnn resize_layer assertion 'getmemoryshapes' hello! i was testing a model with the opencv dnn module to then implement t

hello! i just updated the repo.. maybe with some optimizations it could get to 40-FPS.. now is around 25-30 thanks @bera

heeey! aaah you are right.. my bad! i forgot that in the next networks just some regions are analyzed i just saw it with

@berak i uploaded my code to https://github.com/richipower/PCN-opencv is just the first two stages.. as soon as i finish

okay! i will just get some sushi and then create a github repo.. the names i defined as: ScoresData is the "cls_prob" l

okay! i will just get some sushi and then create a github repo.. the names i defined as: ScoresData is the "cls_prob" l

okay! i will just get some sushi and then create a github repo.. the names i defined as: ScoresData is the "cls_prob" la

okay! i will just get some sushi and then create a github repo.. the names i defined as: ScoresData is the "cls_prob" la

i have both running in caffe and ncnn.. but in mac os :( . caffe is about 30-FPS and ncnn around 7-FPS with the same con

yes, i was looking also in that one. I did the process of setting the inputs and reading the outputs of the networks sim

yes, i was looking also in that one. I did the process of setting the inputs and reading the outputs of the networks sim

uuuh shame :( . i will try to figure out what can be different there and post news if i get something. thanks!

yes! using the dnn module instead of caffe, i ported a lot of algorithms and while using the CPU, dnn is faster than the

yes! using the dnn module instead of caffe, i ported a lot of algorithms and while using the CPU is faster than the caff

dnn module caffe, weird output Hello, i am porting an algorithm to opencv https://arxiv.org/pdf/1804.06039.pdf , the mod

hello!, i am having the same issue with the version 3.4.1, the note is still there, i cannot find the file that it refe

Hello,

i am implementing a facedetector in opencv, Single Stage Headless detector SSH using the pretrained model provided, modifying the .prototxt file to be compatible without python layers accordingly to the example described in faster_rcnn_opencv which would be something like the following for each of the python proposal layers:

layer {
name: 'm2@ssh_proposal'
type: 'Proposal'
bottom: 'm2@ssh_cls_prob_reshape_output'
bottom: 'm2@ssh_bbox_pred_output'
bottom: 'im_info'
top: 'm2@ssh_boxes'
top: 'm2@ssh_cls_prob'
proposal_param {
feat_stride: 16
scale: 4
scale: 8
ratio: 1
}
}

and my code looks like:

String model = "SSH.caffemodel";
String proto = "SSH.prototxt";
Net SSH_net = readNetFromCaffe(proto, model);

Mat img = imread("test.jpg");
resize(img, img, Size(224, 224));
img = img - Scalar(102.9801, 115.9465, 122.7717);

Mat inputBlob = blobFromImage(img, 1.0f, Size(), Scalar(), true, false);
Mat imInfo = (Mat_<double>(1, 3) << 224, 224, 1);

SSH_net.setInput(inputBlob, "data");
SSH_net.setInput(imInfo, "im_info");

SSH_net.forward();

The network is being created succesfully, but at the moment of forwarding the network it just crashes.. I havent found any workaround for this, does anyone has any suggestions or ideas? or have been facing this issue? Any help is appreciated! thank you!

@dkurt woow thank you for the very fast answer and solution, i just compiled with your PR and it works in both C++ and p

application stopped working with caffe network dnn module, forward() Hello, i am implementing a facedetector in opencv

Implementation of "MTCNN" with new dnn module using the caffe models Hi, i am trying to implement the paper https://kpz

@StevenPuttemans do you have maybe in the meantime your solution for the peak finder problem? :)

@dipesh could you explain how did you fixed it? i am having the same issue :( and i havent been able to solve it.. many thanks!