tgandor

So finally, I'd rather do it like this: ``` weights_header = np.ndarray(shape=(3,), dtype='int32', buffer=weights_file.read(12)) if weights_header[0] > 0 or weights_header[1] > 1: seen = np.ndarray(shape=(1,), dtype='int64', buffer=weights_file.read(8)) else: seen =...

I'm also having this issue. I suspected RGB and BGR channel ordering, but it seems to have little effect. My average recall on training is far greater than 0.5 (approaching...

I would rather go for 'smart' behavior, i.e.: `def __init__(self, leases_file):`, and then: if `leases_file` is an "open stream", then process it directly; maybe detect `b'\x1f\x1b'` and then gunzip it...

I also first tried `'>= 3.5'`, which would be the best, but more dissapointingly, my next try was: ``` [requires] python_version = "3.5,3.6,3.7,3.8" ``` And I've got: ``` Specifier python_version...