aboutsummaryrefslogtreecommitdiff
Commit message (Collapse)AuthorAge
* speedup testout in lm_trainertxh182015-12-25
|
* ...txh182015-12-25
|
* the grulm baseline seems to work finetxh182015-12-25
|
* trying to find a fimpler lstm_v2, then aborttxh182015-12-24
|
* get a new log for rnnlm_h300txh182015-12-23
|
* changed affine_recurrent used in lm to affine_recurrent_plusvectxh182015-12-23
|
* added copy_rows_fromd_by_colidx for clearer namingtxh182015-12-22
|
* ...txh182015-12-22
|
* give a update_select_rows a more proper nametxh182015-12-22
|
* added a garbace collect in tnntxh182015-12-21
|
* added compressed_label support in the readertxh182015-12-21
|
* small mistake in layersTtxh182015-12-20
|
* added find_param method for layersTtxh182015-12-20
|
* bug fix in lmptb.vocabtxh182015-12-13
|
* ...txh182015-12-13
|
* move lmvocab:read_line to lmutiltxh182015-12-13
|
* bug fix: added check in the select_linear kerneltxh182015-12-11
|
* ...txh182015-12-10
|
* merge conflict resolvetxh182015-12-10
|\
| * fix the bug in freeing submatrix; add `offset` to Matrix structurebugfix-matrixfreeDeterminant2015-12-10
| |
| * Merge branch 'master' of github.com:Nerv-SJTU/nervDeterminant2015-11-23
| |\
| | * Merge pull request #7 from yimmon/masterTed Yin2015-11-23
| | |\ | | | | | | | | support kaldi decoder
| | | * add need_key for sequence trainingYimmon Zhuang2015-11-23
| | | |
| | | * support kaldi decoderYimmon Zhuang2015-10-14
| | | |
| * | | use rearrange = true and frm_trim = 5 in settings and reproduce the results ↵Determinant2015-11-23
| |/ / | | | | | | | | | again
* | | removed flush_all for every mb in process_birnntxh182015-12-10
| | |
* | | bug fix for recent changes in tnntxh182015-12-10
| | |
* | | ...txh182015-12-10
| | |
* | | bilstm_v2 did not run welltxh182015-12-10
| | |
* | | ...txh182015-12-09
| | |
* | | ...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 ↵txh182015-12-03
| | | | | | | | | | | | another way(like in the paper) of dropout for lstm.h after combinerL