Nearest-Neighbour-Search-Neural-Networks-Product-Quantization/TEXMEX/WNN Library/QuantHammingCanonicalIndices.m

function [iCminDist]=QuantHammingCanonicalIndices(CWidx,nNets)

N=size(CWidx,1);
iCminDist=zeros(1,N);
idxs=1:nNets;
%rPermidx=randperm(N,nNets);
pperc=[];

[~, ~, icw]=unique(CWidx,'rows');
uicw=unique(icw);
luicw=length(uicw);
%uniNets=nNets/luicw;
rPermidx=[];
for jj=1:luicw
    ficw=find(icw==uicw(jj));
    adaptidx=randperm(length(ficw),floor(nNets*length(ficw)/N));
    %size(adaptidx)
    %size(ficw(adaptidx))
    rPermidx=[rPermidx ficw(adaptidx)'];
end

newidx=nNets-length(rPermidx);

if newidx>0
    totpermidx=randperm(N);
    toremidx=rPermidx(rPermidx==newidx);
    totpermidx(toremidx)=[];
    selectidx=randperm(length(totpermidx),newidx);
    rPermidx=[rPermidx totpermidx(selectidx)];
end

size(rPermidx);

for ii=1:N

    if any(rPermidx==ii)
        iCminDist(ii)=find(rPermidx==ii,1,'first');
    else
        % Approximation of half of the hamming distance
        dH=sum(bsxfun(@ne,CWidx(rPermidx,:),repmat(CWidx(ii,:),nNets,1))');
        allOfTheMins=idxs(dH==min(dH));
        iCminDist(ii)=allOfTheMins(randi(length(allOfTheMins)));
        %[~,iCminDist(ii)]=min(dH);
    end
        perc=sprintf('%2.2f%%',ii/N*100);
        fprintf(1,'%s',sprintf('\b')*ones(1,length(pperc)));
        fprintf(1,'%s',perc);pperc=perc;  
end
fprintf(1,'%s',sprintf('\b')*ones(1,length(pperc)));
end