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

	Commit message (Collapse)	Author	Age
*	fixed direct update, did not know the result	txh18	2015-11-16
\|
*	added timer	txh18	2015-11-15
\|
*	merge lr schedule change	txh18	2015-11-15
\|\ \| \| \| \| \| \|	Merge branch 'txh18/rnnlm' of github.com:Nerv-SJTU/nerv into txh18/rnnlm
\| *	got good PPL for H400...	cloudygoose	2015-11-15
\| \|
* \|	added msr_sc set	txh18	2015-11-15
\|/
*	small bug: lr_half	txh18	2015-11-13
\|
*	...	txh18	2015-11-13
\|
*	added random seed	txh18	2015-11-13
\|
*	added loadstring	txh18	2015-11-13
\|
*	saving param file for every iter	txh18	2015-11-13
\|
*	change ppl_net to ppl_all	txh18	2015-11-13
\|
*	added wcost for select_linear layer	txh18	2015-11-12
\|
*	cleaning files...	txh18	2015-11-12
\|
*	get good PPL for h300, see m-tests/LOG-tnn-h300	txh18	2015-11-12
\|
*	added a little debug info in reader	txh18	2015-11-11
\|
*	got good result when batch_size=1, strange!	txh18	2015-11-11
\|
*	bug fix : changed zero-filling across borders	txh18	2015-11-10
\|
*	small bug in lmseqreader	txh18	2015-11-09
\|
*	small bug about zeroing error	txh18	2015-11-09
\|
*	another bit error bug found	txh18	2015-11-09
\|
*	serious bug about bit operation in tnn	txh18	2015-11-08
\|
*	switched to softmax_ce_t	txh18	2015-11-08
\|
*	ih[0] nolonger zero	txh18	2015-11-08
\|
*	trying to test softmax_ce_t	txh18	2015-11-08
\|
*	meet a bug, don not know why	txh18	2015-11-07
\|
*	ready to test on ptb	txh18	2015-11-07
\|
*	writing the scheduler	txh18	2015-11-06
\|
*	added cross-border flush	txh18	2015-11-06
\|
*	first small tnn test seems to work	txh18	2015-11-06
\|
*	working on TNN:net_propagate	txh18	2015-11-03
\|
*	still working on TNN	txh18	2015-11-03
\|
*	...	txh18	2015-11-02
\|
*	...	txh18	2015-11-02
\|
*	still working on the tdag layer	txh18	2015-11-01
\|
*	start implementing tdag_layer	txh18	2015-10-30
\|
*	finished a simple version of lmseqreader	txh18	2015-10-30
\|
*	still working in lmseqreader	txh18	2015-10-30
\|
*	doing	txh18	2015-10-28
\|
*	TODO:implement lmseqreader	txh18	2015-10-28
\|
*	changed copy_rows_fromd_by_idx a bit to make it clearer	txh18	2015-10-28
\|
*	added update_select_rows to doc	txh18	2015-10-28
\|
*	added update_select_rows for select_linear:update speed-up	txh18	2015-10-27
\|
*	using copy_rows_fromd for select-liner:propagate, TODO:speed up ↵	txh18	2015-10-26
\| \| \| \|	select-linear:update
*	discovered a copy_rows_fromd_by_idx that can be used	txh18	2015-10-26
\|
*	simple doc change	txh18	2015-10-25
\|\
\| *	changed doc pointer in the main markdown	txh18	2015-10-25
\| \|
* \|	added timer for profiling	txh18	2015-10-25
\| \|
* \|	lmptb can be run after merge from master	txh18	2015-10-23
\| \|
* \|	Just come back, let's merge the new master	txh18	2015-10-23
\|\\| \| \| \| \| \| \|	Merge branch 'master' into txh18/rnnlm
\| *	Merge pull request #6 from yimmon/master	Ted Yin	2015-10-12
\| \|\ \| \| \| \| \| \|	support batch_resize (sequence training related layers are in kaldi_seq)