void trainCBOW(){
if(rank == 0){
readVocab();
InitNet();
if (negative > 0){
InitUnigramTable();
}
}
trainModelParallelCBOW();
}
void LearnEmbeddings(TVVec<TInt, int64>& WalksVV, int& Dimensions, int& WinSize,
int& Iter, bool& Verbose, TIntFltVH& EmbeddingsHV) {
TIntIntH RnmH;
TIntIntH RnmBackH;
int64 NNodes = 0;
//renaming nodes into consecutive numbers
for (int i = 0; i < WalksVV.GetXDim(); i++) {
for (int64 j = 0; j < WalksVV.GetYDim(); j++) {
if ( RnmH.IsKey(WalksVV(i, j)) ) {
WalksVV(i, j) = RnmH.GetDat(WalksVV(i, j));
} else {
RnmH.AddDat(WalksVV(i,j),NNodes);
RnmBackH.AddDat(NNodes,WalksVV(i, j));
WalksVV(i, j) = NNodes++;
}
}
}
TIntV Vocab(NNodes);
LearnVocab(WalksVV, Vocab);
TIntV KTable(NNodes);
TFltV UTable(NNodes);
TVVec<TFlt, int64> SynNeg;
TVVec<TFlt, int64> SynPos;
TRnd Rnd(time(NULL));
InitPosEmb(Vocab, Dimensions, Rnd, SynPos);
InitNegEmb(Vocab, Dimensions, SynNeg);
InitUnigramTable(Vocab, KTable, UTable);
TFltV ExpTable(TableSize);
double Alpha = StartAlpha; //learning rate
#pragma omp parallel for schedule(dynamic)
for (int i = 0; i < TableSize; i++ ) {
double Value = -MaxExp + static_cast<double>(i) / static_cast<double>(ExpTablePrecision);
ExpTable[i] = TMath::Power(TMath::E, Value);
}
int64 WordCntAll = 0;
// op RS 2016/09/26, collapse does not compile on Mac OS X
//#pragma omp parallel for schedule(dynamic) collapse(2)
for (int j = 0; j < Iter; j++) {
#pragma omp parallel for schedule(dynamic)
for (int64 i = 0; i < WalksVV.GetXDim(); i++) {
TrainModel(WalksVV, Dimensions, WinSize, Iter, Verbose, KTable, UTable,
WordCntAll, ExpTable, Alpha, i, Rnd, SynNeg, SynPos);
}
}
if (Verbose) { printf("\n"); fflush(stdout); }
for (int64 i = 0; i < SynPos.GetXDim(); i++) {
TFltV CurrV(SynPos.GetYDim());
for (int j = 0; j < SynPos.GetYDim(); j++) { CurrV[j] = SynPos(i, j); }
EmbeddingsHV.AddDat(RnmBackH.GetDat(i), CurrV);
}
}
