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

	Commit message (Collapse)	Author	Age
*	enhanced m-test/lm_sample	txh18	2016-02-05
\|
*	..	txh18	2016-02-05
\|
*	...	txh18	2016-02-05
\|
*	made lm sampling code cleaner	txh18	2016-02-05
\|
*	added same_io option to lm_seq_reader	txh18	2016-02-03
\|
*	like data of twitter from choose2 to choose	txh18	2016-01-30
\|
*	select gpu code from mfy	txh18	2016-01-29
\|
*	moved gru_t to tnn/layersT	txh18	2016-01-29
\|
*	added logp addition to LMResult	txh18	2016-01-27
\|
*	tiny bug fix in LMVocab	txh18	2016-01-21
\|
*	used prefixsum_row operation to speed up sampling on the softmax output	txh18	2016-01-20
\|
*	big fixes about lm_sampler	txh18	2016-01-19
\|
*	added lm_sampler, todo:test it	txh18	2016-01-19
\|
*	developing sample_grulm	txh18	2016-01-18
\|
*	added bigrulm_ptb_main.lua	txh18	2016-01-13
\|
*	...	txh18	2016-01-12
\|
*	added wordprob into gru_ptb_main.lua	txh18	2016-01-11
\|
*	added word_prob feature to lm_trainer	txh18	2016-01-06
\|
*	...	txh18	2016-01-01
\|
*	try whole vocab for twitter	cloudygoose	2015-12-28
\|
*	added unk_cn to LMResult	cloudygoose	2015-12-28
\|
*	revised twitter set for grulm	cloudygoose	2015-12-28
\|
*	...	txh18	2015-12-25
\|
*	speedup testout in lm_trainer	txh18	2015-12-25
\|
*	...	txh18	2015-12-25
\|
*	the grulm baseline seems to work fine	txh18	2015-12-25
\|
*	trying to find a fimpler lstm_v2, then abort	txh18	2015-12-24
\|
*	get a new log for rnnlm_h300	txh18	2015-12-23
\|
*	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
\|
*	added compressed_label support in the reader	txh18	2015-12-21
\|
*	bug fix in lmptb.vocab	txh18	2015-12-13
\|
*	...	txh18	2015-12-13
\|
*	move lmvocab:read_line to lmutil	txh18	2015-12-13
\|
*	...	txh18	2015-12-10
\|
*	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
\|
*	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
\|