Transforms original labels into the range [0, nb_labels-1] when preprocessing data ,but where is '0'?

[guoyang007]

the function 'adjust_idx_labels' try to Transforms original labels into the range [0, nb_labels-1], in the file preprocess_data.py, but why to [0,nb_labels-1],not [1,nb_labels]? and now where is the class 0?
I'm now using the dataset to do sth ion the Torch,and there may be an error where 'Assertion t >= 0 && t < n_classes failed'.

So I'm confused about the transform ,looking forward to your answer~

[hsm207]

I think it's [0, nb_labels -1] and not [1, nb_labels] because of the convention of starting to count from 0.

As for where is class 0, class 0 is still in the data. Based on the label_legend.txt file, it looks like class 0 corresponds to the null class i.e. no event of interest. So, we don't need to adjust this since by convention, we label the class that we are not interested in as 0.