What do output values/coordinates from the model represent?

[JLC7]

I am confused about what the model should be outputting by the model here: https://github.com/eriklindernoren/PyTorch-YOLOv3/blob/47b7c912877ca69db35b8af3a38d6522681b3bb3/detect.py#L77

I would expect coordinates [0,1] representing the center of the object, but the values are > 1 and do not seem to to be the final rescaled bound box values. What exactly do the values outputted by the model represent?

Here are some representative values for box predictions from the network when I run detect.py:

[[215.465  73.967  82.987  41.921   ]
 [232.527  75.277  68.669  44.569   ]
 [247.51   75.514  68.231  43.205    ]
 [262.446  75.58   70.544  39.788   ]
 [280.873  75.539  73.744  35.657  ]]

[mroyce1]

Same question here. Any ideas?