Original code of gaussian_radius has been fixed about centernet_pro_max HOT 5 CLOSED

thanks for this useful info!

what's the side effect due to wrong gaussian radius anyway?

from centernet_pro_max.

@fenglv12345 show significant improvement in average recall princeton-vl/CornerNet#110 (comment)

from centernet_pro_max.

got it, will try it

from centernet_pro_max.

thanks for this useful info!

what's the side effect due to wrong gaussian radius anyway?

Lower average recall

from centernet_pro_max.

the code for gaussian radius from CenterNet repo was brought from Cornernet and the gaussian_radius() function is wrong, it has been fixed by the author here is the code
def gaussian_radius(det_size, min_overlap):
height, width = det_size

a1  = 1
b1  = (height + width)
c1  = width * height * (1 - min_overlap) / (1 + min_overlap)
sq1 = np.sqrt(b1 ** 2 - 4 * a1 * c1)
r1  = (b1 - sq1) / (2 * a1)

a2  = 4
b2  = 2 * (height + width)
c2  = (1 - min_overlap) * width * height
sq2 = np.sqrt(b2 ** 2 - 4 * a2 * c2)
r2  = (b2 - sq2) / (2 * a2)

a3  = 4 * min_overlap
b3  = -2 * min_overlap * (height + width)
c3  = (min_overlap - 1) * width * height
sq3 = np.sqrt(b3 ** 2 - 4 * a3 * c3)
r3  = (b3 + sq3) / (2 * a3)
return min(r1, r2, r3)

Please refer to this for formula derivation
princeton-vl/CornerNet#110

for r1 and r2, why is b-sq not b+sq? they all are positive.

from centernet_pro_max.