diff options
| author | Patrick Simianer <simianer@cl.uni-heidelberg.de> | 2012-05-15 00:44:03 +0200 |
|---|---|---|
| committer | Patrick Simianer <simianer@cl.uni-heidelberg.de> | 2012-05-15 00:44:03 +0200 |
| commit | 37050e861de2b216d3a28f79e111b674c5d142ac (patch) | |
| tree | f830d51ca55af1d1a67f2e7bad687cc46480317b /dtrain/pairsampling.h | |
| parent | 7c344de97edac0aa2a6a90c2de9bcf60f15ac000 (diff) | |
loss margin cfg, XYX improved, smooth bleu variant
Diffstat (limited to 'dtrain/pairsampling.h')
| -rw-r--r-- | dtrain/pairsampling.h | 16 |
1 files changed, 11 insertions, 5 deletions
diff --git a/dtrain/pairsampling.h b/dtrain/pairsampling.h index 5085738e..32006a41 100644 --- a/dtrain/pairsampling.h +++ b/dtrain/pairsampling.h @@ -46,11 +46,15 @@ all_pairs(vector<ScoredHyp>* s, vector<pair<ScoredHyp,ScoredHyp> >& training, sc inline void partXYX(vector<ScoredHyp>* s, vector<pair<ScoredHyp,ScoredHyp> >& training, score_t threshold, float hi_lo) { - sort(s->begin(), s->end(), cmp_hyp_by_score_d); unsigned sz = s->size(); + if (sz < 2) return; + sort(s->begin(), s->end(), cmp_hyp_by_score_d); unsigned sep = round(sz*hi_lo); - for (unsigned i = 0; i < sep; i++) { - for (unsigned j = sep; j < sz; j++) { + 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; + for (unsigned i = 0; i < sep_hi; i++) { + for (unsigned j = sep_hi; j < sz; j++) { #ifdef DTRAIN_FASTER_PERCEPTRON if ((*s)[i].model <= (*s)[j].model) { #endif @@ -66,8 +70,10 @@ partXYX(vector<ScoredHyp>* s, vector<pair<ScoredHyp,ScoredHyp> >& training, scor #endif } } - for (unsigned i = sep; i < sz-sep; i++) { - for (unsigned j = sz-sep; j < sz; j++) { + unsigned sep_lo = sz-sep; + while (sep_lo > 0 && (*s)[sep_lo-1].score == (*s)[sep_lo].score) --sep_lo; + for (unsigned i = sep_hi; i < sz-sep_lo; i++) { + for (unsigned j = sz-sep_lo; j < sz; j++) { #ifdef DTRAIN_FASTER_PERCEPTRON if ((*s)[i].model <= (*s)[j].model) { #endif |