How to L2 normalize an array with Swift

问题

I am trying normalize the input of my CoreML model like below, it kind of does something to the array but its quite different then what SKLearn does(I give same input and watch output in these environments). So appereantly I do something wrong.

My Model is trained with Keras and SKlearn and it must do the same normalization as I did using SKLearn Normalizer, which is the default L2 normalizer. What I am doing below apperantly is not equalivant of sklearn, any ideas?

    vDSP_normalizeD(vec, 1, &normalizedVec, 1, &mean, &std, vDSP_Length(count))

    let (normalizedXVec, _, _) = normalize(vec: doubleArray)

Then here I convert normalizedXVec to MLMultiArray and use as input to my predictor

Note: I also tried to convert the normalizer from sklearn using coreml tools but I got errors as seen here:

回答1:

vDSP_normalizeD uses the mean and standard deviation. That is not the same as L2.

The L2 normalization first computes the L2-norm of the vector, which is the same as sqrt(v[0]*v[0] + v[1]*v[1] + ... + v[n]*v[n]) and then it divides each element of the vector by that number.

来源：https://stackoverflow.com/questions/54608649/how-to-l2-normalize-an-array-with-swift