JVR32

Hello everyone, I want to use DIGITS (detectnet) + CAFFE to detect objects in my own dataset. I read some posts about adapting some settings in detectnet to use it...

I guess I got stuck then. I already used the (cropped) training/validation images before (together with a set of negative images that didn't contain the specified objects) to do image...

Suppose I had done it differently, and I would have 9000 training images and 4500 validation images with dimensions 640x640, and the wanted objects were smaller parts of those images...

Hello, Could you please point me in the right direction before I spend at lot of time on annotating images that cannot be used in later processing? You told me...

Thank you very much for the information. In that case, I think it is best that I resize all images to have -more or less- the same dimensions before starting...

Hello, I trained a detection network as follows : All training images (containing the objects I want to detect) can have different dimensions : 480x480 ; 640x640 ; 800x600 ;...

Hello, I trained a network for object detection -> setup was described in my previous post (2 posts above this). As you can see, I resized (before annotating) all the...