Float comparison in histogram normalisation layer

[fepegar]

This float comparison can be problematic.

NiftyNet/niftynet/utilities/histogram_standardisation.py

Line 189 in 9b12da4

diff_perc[diff_perc == 0] = np.inf

I was getting -inf in the output of the function because 1.6e-41 == 0 was returning False. I think an epsilon should be used instead: diff_perc[diff_perc < epsilon] = np.inf.