aboutsummaryrefslogtreecommitdiff
path: root/nerv/examples/lmptb
Commit message (Expand)AuthorAge
* ...txh182015-12-09
* ...txh182015-12-09
* small bugs fix for bilstm scripttxh182015-12-08
* small bugs fixtxh182015-12-07
* ...txh182015-12-07
* lm script change:user can set start_lrtxh182015-12-06
* some log changtxh182015-12-06
* added extend_t for tnn to save GPU memorytxh182015-12-06
* small bug fix on lm train scripttxh182015-12-06
* small bug fix in lm training scripttxh182015-12-06
* small bug fix in lm training scripttxh182015-12-05
* added twitter, added bilstmlm script, todo: test bilstmlmtxh182015-12-05
* changed lstm_t to a more standard versiontxh182015-12-05
* small bug fix for lmptb.lstm_t_v2txh182015-12-04
* trying to use lstm_t_v2 for ptbtxh182015-12-04
* added one_sen_report to lm_process_filetxh182015-12-04
* ...txh182015-12-04
* added testout command for lstmlmtxh182015-12-04
* added log_redirect to SUtiltxh182015-12-04
* applying dropout on lstm.h before combinerL seems bad, PPL only 95, trying an...txh182015-12-03
* added two layers to lstmlm_ptb, todo:test ittxh182015-12-03
* added al_sen_start stat for lmseqreadertxh182015-12-03
* moved tnn to main nerv dir and added it to Makefiletxh182015-12-03
* ...txh182015-12-03
* small bug fix in tnn for se_mode, todo:test ittxh182015-12-02
* added se_mode for lmseqreader, todo:check ittxh182015-12-02
* function name change in LMTrainertxh182015-12-02
* added dropout_t layertxh182015-12-02
* changed thres_mask function of matrix to a more standard apitxh182015-12-02
* got PPL115 for ptb on h300lr1bat10wc1e-4txh182015-12-01
* bug fix for lstm_t layer, t not inclueded in propagate!txh182015-11-30
* small opt for initing tnn:clip_ttxh182015-11-30
* added ooutputGate for lstm_ttxh182015-11-30
* added clip_t for tnntxh182015-11-27
* lstm_tnn can be run, todo:testingtxh182015-11-27
* still working..txh182015-11-26
* working on lstmtxh182015-11-26
* changed auto-generating params, won not save in global_conf.paramtxh182015-11-25
* let affine supported multiple inputstxh182015-11-24
* added wcost for biasparam in lm_trainertxh182015-11-24
* still working on dagL_Ttxh182015-11-24
* completed layerdag_t, now testing...txh182015-11-23
* completed gate_fff layertxh182015-11-23
* implementing GateFFF layertxh182015-11-23
* complete auto-generate paramstxh182015-11-20
* working on automatic parameter for layerstxh182015-11-20
* changed work_dir settingtxh182015-11-18
* h300 and h400 worked well, log addedtxh182015-11-18
* switch to kernel updatetxh182015-11-17
* bug fix for select_linear layer-by-layer updatetxh182015-11-17