Mishal077's profile - activity

Hey i just want to know which framework this .net model belongs to is it the Torch7 or obtained by ONNX.I am not clear a

Are you using it with JAVA based IDE on windows and not on android?

@berak i think i am doing something wrong here can you share the complete java file.

I am facing the issues with the Mat result = new Mat(); Imgproc.resize(segm, segm, frame.size());

I found that OpenCV resize is missing support for certain combinations of input and output depths (numeric types), and

Got it. @berak @dkurt I am trying to get the live feed from Mobile Camera using JavaCameraPreview. I am developing on Ne

I am using the OpenCV SDK 3.4.4 for Android, I think it is the latest one? Ok I am trying the guess as mentioned

@dkurt Android the size function is not there.

Android the size function is not there.

System.out.println(res.size(0)+" "+res.size(1)+" "+res.size(2)+" "+res.size(3)); Here the code is in native OpenCV in n

DNN.net.forward() in Android String model = getPath("model.net", getApplicationContext()); net = Dnn.readNet(model);

I am using a model with extension .net which works perfectly fine in Python.

net = cv2.dnn.readNet('models/model.net')
blob = cv2.dnn.blobFromImage(image, 1 / 255.0, (1024, 512), 0,
        swapRB=True, crop=False)

but when I tried to do the same on android I got blob size -1*-1 ideal it should not it should be in the passed dimension only.

I had used this link for the reference. https://docs.opencv.org/3.4/d0/d6c/tu...

Yup, it segmentation code in python. Can you suggest any approach how i can get this done on android. Working hard on th

Need Equivalent code in JAVA (numClasses, height, width) = output.shape[1:4] # our output class ID map will be num_

Yup i had prototxt file for the same still getting the issue. I am trying the other way around here switch to enet-mode

I uncommented the cvtColor & now i am getting this Assertion failed (blobs.size() != 0) in virtual bool cv::dnn::C

I am using the Caffe Model Enet https://modeldepot.io/timosaemann/enet Yup Height & Width are perfect for them

DNN.net.forward() in Android String model = getPath("model.net", getApplicationContext()); net = Dnn.readNet(model);

DNN blobFromImage gives -1*-1 in Android. I am using a model with extension .net which works perfectly fine in Python.