Ask Your Question

damiya14's profile - activity

2020-05-11 14:58:33 -0500 received badge  Popular Question (source)
2017-06-05 06:09:28 -0500 commented answer How to load ANN in opencv 3.xxx

i used that method but i get a SOGSEGV error.

in my training method the input is 1 row and 6400 cols (80x80 gray scale image). and in my prediction part i give the same size Mat in to the network but still get an error.

2017-06-05 04:50:27 -0500 commented answer How to start with neural network implementation with Opencv and C++??

@berak, Then i use this to predict but i get a SIGSEGV error.

ann->predict(features, results);
2017-06-05 04:28:26 -0500 commented answer How to start with neural network implementation with Opencv and C++??

how can i save this ANN and load it again and input image and classify it?

2017-06-05 04:09:51 -0500 commented answer How to load ANN in opencv 3.xxx

i want to input one image in to the model and get the classification. how can i do this?

2017-06-02 07:16:24 -0500 commented answer How to load ANN in opencv 3.xxx

Thank You!!

2017-06-02 07:15:36 -0500 commented question Vehicle grill texture orientation detection?

i will be training it with logo and non-logo images...

2017-05-31 06:10:19 -0500 asked a question How to load ANN in opencv 3.xxx

i have trained an ANN and saved it. now i want to load it and input images in to it and classify. how can i do this? example code will be so helpful. Thanks

2017-05-31 06:07:37 -0500 commented question Vehicle grill texture orientation detection?

im trying to use ANN for logo detection just want to know how to load the saved ann file and input an image and get an out put from the ANN

2017-05-25 13:48:24 -0500 commented question Vehicle grill texture orientation detection?

you are suggesting that u should use machine learning or?

2017-05-25 13:48:24 -0500 received badge  Commentator
2017-05-25 13:43:52 -0500 asked a question how to use ANN with multi cores

I am using ANN library in opencv 3.xx . currently it only use one core in my processor. is there a way to use more cores and is there a way to use gpu for training the network.

2017-05-05 03:49:26 -0500 commented answer How to start with neural network implementation with Opencv and C++??

train_classes.at<float>(i, train_labels.at<int>(i)) = 1.f;

What does this line do? Please explain and thanks!

2017-03-13 20:47:25 -0500 commented question Vehicle grill texture orientation detection?

thanks i edited the question :)

2017-03-13 01:15:06 -0500 asked a question Vehicle grill texture orientation detection?

I am doing a vehicle logo recognition. And in order to logo localization i wont to wether the know the grill texture is vertical or horizontal. So then i can suppress the grill texture with sobel operator and get an accurate logo position or area.

How can i find out the grill texture orientation?

Vertical Grill Horizontal Grill

2017-02-22 01:44:05 -0500 asked a question opencv on mac

I want to install opencv to work with NetBeans. I have done lots of attempts but failed. NetBeans successfully loads the header files and the code dose't shows any errors. But when I run it it gives me a build fail.

In NetBeans linker I canot find the opencv in pig-config

How can I solve this problem?

2017-02-22 01:41:36 -0500 asked a question Opencv & NetBeans on mac

I want to install opencv to work with NetBeans. I have done lots of attempts but failed. NetBeans successfully loads the header files and the code dose't shows any errors. But when I run it it gives me a build fail.

In NetBeans linker I canot find the opencv in pig-config

How can I solve this problem?

2017-01-18 02:55:51 -0500 commented answer Load a csv containing string

Thank you!!

2017-01-18 01:55:27 -0500 asked a question Load a csv containing string

I have a csv file that contains file paths.

eg:

col1  |         col2
 1    | 173/d234c34a87ffb7.jpg
 1    | 173/de9f04d2497222.jpg

I want to read this file and store it in opencv. How can i do it? I have tried the code below but it only reads col1 correct.

CvMLData cvml;
    cvml.read_csv("/home/damiya/test/compcars/sv_data/CSV/asd.csv");
    cvml.set_response_idx(0);
    const CvMat* vs = cvml.get_values();
    cout << "Rows: " << vs->rows << " Cols: " << vs->cols << endl;
    for(int i = 0; i < vs->rows; i++ )
    {
        cout << vs->data.fl[i*vs->cols] << "\n";

    }
2016-12-31 01:26:41 -0500 received badge  Student (source)
2016-11-03 09:06:25 -0500 commented answer Cv::ml::TrainData::loadFromCSV Parameters

it's done still wrong :( :( returns the same value

2016-11-03 08:30:26 -0500 commented answer Cv::ml::TrainData::loadFromCSV Parameters

its still running :(

2016-11-03 08:11:15 -0500 commented answer Cv::ml::TrainData::loadFromCSV Parameters

hey,

i tried train_auto() and it takes a lot of time. Does it take a lot of time?

2016-11-02 03:16:43 -0500 commented answer Cv::ml::TrainData::loadFromCSV Parameters

its 31mb. i tried different kernel types such as linear,rbm, and poly but every time its wrong.

i will try train_auto().. hops that works :) :)

2016-11-02 02:46:06 -0500 commented answer Cv::ml::TrainData::loadFromCSV Parameters

my csv file contains hsv rgb and yCrCb data for each pixel this is csv file.

first column contains the label. then in order R G B H S V Y Cr Cb and it repeats.

2016-11-02 02:26:03 -0500 marked best answer Cv::ml::TrainData::loadFromCSV Parameters

i want to load a csv file as train data.

in csv file first column contains the labels (which is 1 - 12) other columns contains the data.

cv::ml::TrainData::loadFromCSV  (   const String &  filename,
int     headerLineCount,
int     responseStartIdx = -1,
int     responseEndIdx = -1,
const String &  varTypeSpec = String(),
char    delimiter = ',',
char    missch = '?' 
)

i am confused with parameters. please explain the parameters.

Thank you!

2016-11-02 02:10:41 -0500 commented answer Cv::ml::TrainData::loadFromCSV Parameters

ok i managed to do it. i am just using two classes (white & silver) So train the svm and use the model as below,

 CvSVM mySVM1;
    mySVM1.load("/home/damiya/test/Sakura/my.xml");
    .
    .
    .
    .
    float response = mySVM1.predict(sampleMat);

but the modele returns only one class every time. (ex. it returns everything as white even i feed the features that i used to train it)