Using images for input to ST Model zoo models

[Supraja_Kurella]

I am using the object detection code from ST model zoo. 
I have a small image of 4X4 example: 

const uint8_t myImage[NN_HEIGHT] [ NN_WIDTH]= {

// Row 0 (all black)

{ 255, 0, 0, 0},

// Row 1 (black, then white dot, then black)

{ 0, 255, 255, 0}, // Pixels 1 and 2 are white (center of a 2x2 dot)

// Row 2 (black, then white dot, then black)

{0, 255, 255, 0},// Pixels 1 and 2 are white

// Row 3 (all black)

{0, 0, 0, 0}

};

I want to see the output as number of dots.
I dont use the camera or display unit of the N6-DK board and I am using memcpy to load the image to the input buffer(nn_in)

The image is also loading into the input buffer as when I put a bp at the memcpy line and see nn_in its first value is shown as 255 'y'
but when I see the output which is stored in pp_output the number of objects detected are 0.
Why do i see that value??
Is using memcpy to load images to input buffer correct?
If not, why and how can I adopt another workflow?
Is there an issue with my image input??

Thanks in advance!

[Julian E.]

Hello @Supraja_Kurella,

 

You are working with 4x4 images to detect white dots.

You gave the example of:

{ 255, 0    , 0    , 0}

{ 0    , 255, 255, 0}

{0     , 255, 255, 0}

{0     , 0    , 0    , 0}

And so here your output should be 5, correct?

 

You mentioned model zoo code? Are you using one of the models? Did you retrain one? I doubt that the input model form the code you use is of size 4x4.

Do you perform some simple tests here? I don't see the need to use AI for that.

 

Have a good day,

Julian

 

[Supraja_Kurella]

I used object detection code from the model zoo and commented out the camera code and used memcpy to load my image to input buffer. 

Is there anything else I need to do..?