Understanding unnormalized_height and unnormalized_width

[mrgloom]

https://github.com/TropComplique/FaceBoxes-tensorflow/blob/545ec4f4f3c55c3592ee189ed56a11a3fd017194/src/anchor_generator.py#L121

I wonder why we make division in one case, but do multiplication in another case?

ratio_sqrt = tf.sqrt(aspect_ratio)
unnormalized_height = scale / ratio_sqrt
unnormalized_width = scale * ratio_sqrt

[TropComplique]

Because then

sqrt(unnormalized_height * unnormalized_width) = scale,
unnormalized_width / unnormalized_height = aspect_ratio

Also see my definitions of aspect_ratio and scale: https://github.com/TropComplique/FaceBoxes-tensorflow/blob/master/src/anchor_generator.py#L21.

[mrgloom]

width, height are in [0,1] range? Why then width and height depend on image size. (in 5.)?