I was getting a RuntimeWarning: overflow encountered in scalar negative for offset = -low * scale in dataset/randaugment.py:32:.
The reason is that low is of class 'numpy.uint8', offset assumes this datatype, leading to problems in cases where scale is a floating point number, e.g. scale=1.0805084745762712, low=2. This leads to a wrong offset calculation because of the overflow, e.g. with offset: 274.4491525423729.
The bug could be easily fixed with casting the type of low as in offset = -np.float64(low) * scale.
I was getting a
RuntimeWarning: overflow encountered in scalar negativeforoffset = -low * scaleindataset/randaugment.py:32:.The reason is that
lowis ofclass 'numpy.uint8',offsetassumes this datatype, leading to problems in cases wherescaleis a floating point number, e.g.scale=1.0805084745762712, low=2. This leads to a wrong offset calculation because of the overflow, e.g. withoffset: 274.4491525423729.The bug could be easily fixed with casting the type of
lowas inoffset = -np.float64(low) * scale.