Image batching

[arikga]

Hi there,

I'm looking to find a way to detect an objects in a very large image, and since the image is scaled to the net sizes I'm losing a lot of information in the original image.

So my plan is to read the Large images, divide it to several ROIs (rectangles) and send them simulations to the net forward pass.
To do this I will probably need to use the set_batch_network(&net, ROI_num) and concatenate images when memcopy them to CUDA, but how will get the results of for each ROI?

The concept is it possible to do?

[prabindh]

There are a number of ways to do it - what is the size of your original image, and what is it you are resizing it to ?

[arikga]

Hi,
the size of the image is 1280960 so I am attend to divide the full frame into 6 rectangles (3 in the width and 2 in the height)
each rectangle will resize to the YOLO net sizes (416416)