aboutsummaryrefslogtreecommitdiff
path: root/nerv/lib
Commit message (Expand)AuthorAge
* complete bp of softmax layerQi Liu2016-06-21
* add relu layerQi Liu2016-04-29
* support SeqBuffer decoding; fix bugs in finding paramsalpha-4Determinant2016-04-18
* Merge branch 'master' of github.com:liuq901/nerv into liuq901-masterDeterminant2016-03-15
|\
| * add total time on profileQi Liu2016-03-15
| * add mask on softmax_ceQi Liu2016-03-15
* | ready for alpha-2 releaseDeterminant2016-03-12
|/
* fix bugQi Liu2016-03-11
* update diagonlal lstmQi Liu2016-03-11
|\
| * update LSTM layerQi Liu2016-02-24
* | add GPU auto selectionDeterminant2016-03-02
* | add options to main entry `nerv`; fix a bug in handling `cudaSetDevice` errorDeterminant2016-03-02
* | add network config for timit baselineDeterminant2016-02-29
* | clean up codeDeterminant2016-02-24
* | add CuContext/MContextwrapped-handlesDeterminant2016-02-24
|/
* ...tnnDeterminant2016-02-17
* try to merge manuallyDeterminant2016-02-17
* pass cflags to nvcc correctly; add omitted func declDeterminant2016-02-16
* move curand_gen out of the matrix layoutDeterminant2016-02-15
* try a basic mergeDeterminant2016-02-15
* added copy_rows_fromd_by_colidx for clearer namingtxh182015-12-22
* give a update_select_rows a more proper nametxh182015-12-22
* bug fix: added check in the select_linear kerneltxh182015-12-11
* merge conflict resolvetxh182015-12-10
|\
| * fix the bug in freeing submatrix; add `offset` to Matrix structurebugfix-matrixfreeDeterminant2015-12-10
* | ...txh182015-12-09
* | changed thres_mask function of matrix to a more standard apitxh182015-12-02
* | added rand_uniform and thres_mask for cumatrixtxh182015-12-01
* | bug fix: tanh implementation could cause nantxh182015-11-29
* | added tanh operation for matrixtxh182015-11-25
|/
* add cflag __NERV_FUTURE_CUDA_7Determinant2015-11-23
* small coding style changetxh182015-11-18
* added atomicAdd for select_linear update, however, the result still seems unr...txh182015-11-17
* using atomicAdd for select_linear updatetxh182015-11-17
* changed copy_rows_fromd_by_idx a bit to make it clearertxh182015-10-28
* added update_select_rows for select_linear:update speed-uptxh182015-10-27
* move sequence related layers to kaldi_seqYimmon Zhuang2015-10-10
* kaldi mpe training supportYimmon Zhuang2015-09-18
* support gpu bufferingDeterminant2015-08-28
* add profiling for copy_rows_fromh_by_idxDeterminant2015-08-14
* add embedding_exampleDeterminant2015-08-04
* added matrix:clip, TODO:testingcloudygoose2015-07-08
* bug fix: Matrix space did not freecloudygoose2015-07-02
* ...Determinant2015-06-26
* [a little big]matrix dim added, now use m:dim() to determine whether vector o...cloudygoose2015-06-25
* 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.