nerv - Lua-based toolkit for high-performance deep learning

	Commit message (Collapse)	Author	Age
*	changed affine_recurrent used in lm to affine_recurrent_plusvec	txh18	2015-12-23
\|
*	added copy_rows_fromd_by_colidx for clearer naming	txh18	2015-12-22
\|
*	...	txh18	2015-12-22
\|
*	give a update_select_rows a more proper name	txh18	2015-12-22
\|
*	added a garbace collect in tnn	txh18	2015-12-21
\|
*	added compressed_label support in the reader	txh18	2015-12-21
\|
*	small mistake in layersT	txh18	2015-12-20
\|
*	added find_param method for layersT	txh18	2015-12-20
\|
*	bug fix in lmptb.vocab	txh18	2015-12-13
\|
*	...	txh18	2015-12-13
\|
*	move lmvocab:read_line to lmutil	txh18	2015-12-13
\|
*	bug fix: added check in the select_linear kernel	txh18	2015-12-11
\|
*	...	txh18	2015-12-10
\|
*	merge conflict resolve	txh18	2015-12-10
\|\
\| *	fix the bug in freeing submatrix; add `offset` to Matrix structurebugfix-matrixfree	Determinant	2015-12-10
\| \|
\| *	Merge branch 'master' of github.com:Nerv-SJTU/nerv	Determinant	2015-11-23
\| \|\
\| \| *	Merge pull request #7 from yimmon/master	Ted Yin	2015-11-23
\| \| \|\ \| \| \| \| \| \| \| \|	support kaldi decoder
\| \| \| *	add need_key for sequence training	Yimmon Zhuang	2015-11-23
\| \| \| \|
\| \| \| *	support kaldi decoder	Yimmon Zhuang	2015-10-14
\| \| \| \|
\| * \| \|	use rearrange = true and frm_trim = 5 in settings and reproduce the results ↵	Determinant	2015-11-23
\| \|/ / \| \| \| \| \| \| \| \| \|	again
* \| \|	removed flush_all for every mb in process_birnn	txh18	2015-12-10
\| \| \|
* \| \|	bug fix for recent changes in tnn	txh18	2015-12-10
\| \| \|
* \| \|	...	txh18	2015-12-10
\| \| \|
* \| \|	bilstm_v2 did not run well	txh18	2015-12-10
\| \| \|
* \| \|	...	txh18	2015-12-09
\| \| \|
* \| \|	...	txh18	2015-12-09
\| \| \|
* \| \|	...	txh18	2015-12-09
\| \| \|
* \| \|	small bugs fix for bilstm script	txh18	2015-12-08
\| \| \|
* \| \|	small bugs fix	txh18	2015-12-07
\| \| \|
* \| \|	...	txh18	2015-12-07
\| \| \|
* \| \|	lm script change:user can set start_lr	txh18	2015-12-06
\| \| \|
* \| \|	some log chang	txh18	2015-12-06
\| \| \|
* \| \|	added extend_t for tnn to save GPU memory	txh18	2015-12-06
\| \| \|
* \| \|	small bug fix on lm train script	txh18	2015-12-06
\| \| \|
* \| \|	small bug fix in lm training script	txh18	2015-12-06
\| \| \|
* \| \|	small bug fix in lm training script	txh18	2015-12-05
\| \| \|
* \| \|	added twitter, added bilstmlm script, todo: test bilstmlm	txh18	2015-12-05
\| \| \|
* \| \|	changed lstm_t to a more standard version	txh18	2015-12-05
\| \| \|
* \| \|	small bug fix for lmptb.lstm_t_v2	txh18	2015-12-04
\| \| \|
* \| \|	trying to use lstm_t_v2 for ptb	txh18	2015-12-04
\| \| \|
* \| \|	added one_sen_report to lm_process_file	txh18	2015-12-04
\| \| \|
* \| \|	...	txh18	2015-12-04
\| \| \|
* \| \|	added testout command for lstmlm	txh18	2015-12-04
\| \| \|
* \| \|	added log_redirect to SUtil	txh18	2015-12-04
\| \| \|
* \| \|	applying dropout on lstm.h before combinerL seems bad, PPL only 95, trying ↵	txh18	2015-12-03
\| \| \| \| \| \| \| \| \| \| \| \|	another way(like in the paper) of dropout for lstm.h after combinerL
* \| \|	added two layers to lstmlm_ptb, todo:test it	txh18	2015-12-03
\| \| \|
* \| \|	added al_sen_start stat for lmseqreader	txh18	2015-12-03
\| \| \|
* \| \|	moved tnn to main nerv dir and added it to Makefile	txh18	2015-12-03
\| \| \|
* \| \|	...	txh18	2015-12-03
\| \| \|
* \| \|	small bug fix in tnn for se_mode, todo:test it	txh18	2015-12-02
\| \| \|