aboutsummaryrefslogtreecommitdiff
path: root/nerv
Commit message (Collapse)AuthorAge
* changed copy_rows_fromd_by_idx a bit to make it clearertxh182015-10-28
|
* added update_select_rows to doctxh182015-10-28
|
* added update_select_rows for select_linear:update speed-uptxh182015-10-27
|
* using copy_rows_fromd for select-liner:propagate, TODO:speed up ↵txh182015-10-26
| | | | select-linear:update
* discovered a copy_rows_fromd_by_idx that can be usedtxh182015-10-26
|
* added timer for profilingtxh182015-10-25
|
* lmptb can be run after merge from mastertxh182015-10-23
|
* Just come back, let's merge the new mastertxh182015-10-23
|\ | | | | | | Merge branch 'master' into txh18/rnnlm
| * Merge pull request #6 from yimmon/masterTed Yin2015-10-12
| |\ | | | | | | support batch_resize (sequence training related layers are in kaldi_seq)
| | * move sequence related layers to kaldi_seqYimmon Zhuang2015-10-10
| | |
| | * disable batch when sequence trainingYimmon Zhuang2015-10-10
| | |
| | * MMI supportYimmon Zhuang2015-10-08
| | |
| | * kaldi mpe training supportYimmon Zhuang2015-09-18
| | |
| * | enable user to set direct_update in gconf; use direct_update in the exampleDeterminant2015-10-09
| |/
| * ...Determinant2015-08-31
| |
| * support gpu bufferingDeterminant2015-08-28
| |
| * ...Determinant2015-08-26
| |
| * move global_transf to asr_trainer.luaDeterminant2015-08-26
| |
| * add optional parameters to mat:createDeterminant2015-08-25
| |
| * use more general implementation for mat:createDeterminant2015-08-25
| |
| * use default cuda library pathDeterminant2015-08-14
| |
| * add profiling for copy_rows_fromh_by_idxDeterminant2015-08-14
| |
| * ...Determinant2015-08-06
| |
| * make network configuration example file clearerDeterminant2015-08-06
| |
| * fix typoes in nerv.errorDeterminant2015-08-06
| |
| * put global transformation into a separate libraryDeterminant2015-08-05
| |
| * ...Determinant2015-08-04
| |
| * add embedding_exampleDeterminant2015-08-04
| |
| * ...Determinant2015-08-04
| |
* | ...cloudygoose2015-08-11
| |
* | Last port is wrongcloudygoose2015-08-11
| |
* | lmptb ported to herecloudygoose2015-07-23
|/
* added clip to layer_confcloudygoose2015-07-10
|
* added affine_recurrent layercloudygoose2015-07-10
|
* added matrix:clip, TODO:testingcloudygoose2015-07-08
|
* ...cloudygoose2015-07-08
|
* Merge pull request #35 from cloudygoose/masterTed Yin2015-07-02
|\ | | | | fix memory leak: matrix not freed when the ref count is greater than zero
| * bug fix: Matrix space did not freecloudygoose2015-07-02
| |
* | change docDeterminant2015-06-26
|/
* ...Determinant2015-06-26
|
* softmax_ce colsum adapt to matrix change, using [0][0]cloudygoose2015-06-26
|
* [a little big]matrix dim added, now use m:dim() to determine whether vector ↵cloudygoose2015-06-25
| | | | or matrix
* make clean addedcloudygoose2015-06-25
|
* Merge branch 'master' of github.com:Determinant/nervDeterminant2015-06-25
|\ | | | | | | | | | | | | Conflicts: nerv/doc/Makefile nerv/doc/source/conf.py nerv/doc/source/index.rst
| * add sphinx doc (see branch 'gh-pages')Determinant2015-06-21
| |
* | use the conf generated by the latest sphinxDeterminant2015-06-25
|/
* remove useless get_critDeterminant2015-06-25
|
* use the standard nerv error reporting in io libDeterminant2015-06-25
|
* separate non-Lua part of matrix code to a dedicated dirDeterminant2015-06-24
|
* separate non-Lua part of io code to a dedicated dir; code clean-upDeterminant2015-06-23
|
Powered by cgit, Themed by Ted Yin.