diff options
Diffstat (limited to 'dtrain/pairsampling.h')
| -rw-r--r-- | dtrain/pairsampling.h | 15 |
1 files changed, 15 insertions, 0 deletions
diff --git a/dtrain/pairsampling.h b/dtrain/pairsampling.h index 71c8ae59..84be1efb 100644 --- a/dtrain/pairsampling.h +++ b/dtrain/pairsampling.h @@ -23,6 +23,8 @@ all_pairs(vector<ScoredHyp>* s, vector<pair<ScoredHyp,ScoredHyp> >& training, sc { sort(s->begin(), s->end(), cmp_hyp_by_score_d); unsigned sz = s->size(); + bool b = false; + unsigned count = 0; for (unsigned i = 0; i < sz-1; i++) { for (unsigned j = i+1; j < sz; j++) { if (threshold > 0) { @@ -32,7 +34,12 @@ all_pairs(vector<ScoredHyp>* s, vector<pair<ScoredHyp,ScoredHyp> >& training, sc if ((*s)[i].score != (*s)[j].score) training.push_back(make_pair((*s)[i], (*s)[j])); } + if (++count == max) { + b = true; + break; + } } + if (b) break; } } @@ -53,6 +60,8 @@ partXYX(vector<ScoredHyp>* s, vector<pair<ScoredHyp,ScoredHyp> >& training, scor unsigned sep_hi = sep; if (sz > 4) while (sep_hi < sz && (*s)[sep_hi-1].score == (*s)[sep_hi].score) ++sep_hi; else sep_hi = 1; + bool b = false; + unsigned count = 0; for (unsigned i = 0; i < sep_hi; i++) { for (unsigned j = sep_hi; j < sz; j++) { #ifdef DTRAIN_FASTER_PERCEPTRON @@ -65,10 +74,15 @@ partXYX(vector<ScoredHyp>* s, vector<pair<ScoredHyp,ScoredHyp> >& training, scor if ((*s)[i].score != (*s)[j].score) training.push_back(make_pair((*s)[i], (*s)[j])); } + if (++count == max) { + b = true; + break; + } #ifdef DTRAIN_FASTER_PERCEPTRON } #endif } + if (b) break; } unsigned sep_lo = sz-sep; while (sep_lo > 0 && (*s)[sep_lo-1].score == (*s)[sep_lo].score) --sep_lo; @@ -84,6 +98,7 @@ partXYX(vector<ScoredHyp>* s, vector<pair<ScoredHyp,ScoredHyp> >& training, scor if ((*s)[i].score != (*s)[j].score) training.push_back(make_pair((*s)[i], (*s)[j])); } + if (++count == max) return; #ifdef DTRAIN_FASTER_PERCEPTRON } #endif |