missing # in metrics.py

[qsyao]

def _crop_to_bounding_box(mask, bbox_min, bbox_max):
"""Crops a 2D or 3D mask to the bounding box specified by bbox_{min,max}."""

we need to zeropad the cropped region with 1 voxel at the lower,

the right (and the back on 3D) sides. This is required to obtain the

"full" convolution result with the 2x2 (or 2x2x2 in 3D) kernel.

TODO: This is correct only if the object is interior to the

bounding box.

cropmask = np.zeros((bbox_max - bbox_min) + 2, np.uint8)

TODO ......

[veritas9872]

This is still unfixed...