aboutsummaryrefslogtreecommitdiff
Commit message (Collapse)AuthorAge
* fix param_repo:add bugQi Liu2016-05-05
|
* add `no_update` attribute to `nerv.MatrixParam`; add correspondingDeterminant2016-05-03
| | | | settings to `nerv.AffineLayer` and `nerv.LSTMGateLayer`
* add "Main Loop" section to overview docDeterminant2016-05-01
|
* add abstraction section in overviewDeterminant2016-05-01
|
* Merge branch 'master' of ssh://speechlab.sjtu.edu.cn:8022/nerv-dev/nervDeterminant2016-05-01
|\
| * Merge branch 'master' into 'master' mfy432016-04-30
| |\ | | | | | | | | | | | | | | | | | | add relu layer See merge request !2
| | * add relu layerQi Liu2016-04-29
| |/
* / add overview docDeterminant2016-05-01
|/
* back-propagate error to the second head of nerv.MSELayerDeterminant2016-04-28
|
* add doc for repoDeterminant2016-04-28
|
* ...Determinant2016-04-28
|
* add docDeterminant2016-04-28
|
* remove redundant parameters in nerv.ParamRepo:addDeterminant2016-04-21
|
* add doc for ioDeterminant2016-04-20
|
* ...Determinant2016-04-19
|
* ...Determinant2016-04-19
|
* add gitlab ci confDeterminant2016-04-19
|
* add doc for nerv.Network; remove the generated HTML docDeterminant2016-04-19
|
* Merge branch 'master' into 'master' mfy432016-04-19
|\ | | | | | | | | | | | | add projection layer and lstmp layer See merge request !1
| * add projection layer and lstmp layertan tian2016-04-18
|/
* support SeqBuffer decoding; fix bugs in finding paramsalpha-4Determinant2016-04-18
|
* Merge branch 'master' of github.com:Nerv-SJTU/nervalpha-3.4Determinant2016-04-04
|\
| * Merge pull request #37 from liuq901/masterTed Yin2016-03-31
| |\ | | | | | | add general trainer
| | * add randomize into default settingQi Liu2016-03-31
| | |
| | * change ptb exampleQi Liu2016-03-31
| | |
| | * update general trainerQi Liu2016-03-31
| | |
| | * update general trainerQi Liu2016-03-30
| | |
* | | minor changes in asr_trainer.luaDeterminant2016-04-04
|/ /
* / fix bug in passing err_input to network; gen zero vectors for biasalpha-3.3Determinant2016-03-30
|/
* Merge pull request #35 from liuq901/masteralpha-3.2Ted Yin2016-03-29
|\ | | | | fix bug of momentum & update mse layer
| * fix bug of momentum & update mse layerQi Liu2016-03-29
|/
* fix "not implemented" and lstm rebinding bugsalpha-3.1Determinant2016-03-26
|
* add explicit KALDI_BASE setting to READMEalpha-3Determinant2016-03-17
|
* do not chdir while trainingDeterminant2016-03-17
|
* adjust the parameter order of methods from ParamRepoDeterminant2016-03-17
|
* Merge branch 'liuq901-master'Determinant2016-03-17
|\
| * Merge branch 'master' of github.com:liuq901/nerv into liuq901-masterDeterminant2016-03-17
|/| | | | | | | | | Conflicts: nerv/layer/rnn.lua
| * RNN support multiple input & fix network flush bugQi Liu2016-03-17
| |
* | Merge branch 'liuq901-master' into seq-bufferDeterminant2016-03-16
|\ \
| * | merge seq_buffer and change asr_trainer.lua accordinglyDeterminant2016-03-16
| | |
| * | 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
| |
| * fix duplicate bug on <input> & <output>Qi Liu2016-03-15
| |
| * speedup duplicate layerQi Liu2016-03-15
| |
| * speedup border flushQi Liu2016-03-14
| |
| * add seq_bufferQi Liu2016-03-14
| |
* | revise parameter naming of global transfalpha-2Determinant2016-03-13
| |
* | ready for alpha-2 releaseDeterminant2016-03-12
| |
* | Merge pull request #31 from liuq901/masterTed Yin2016-03-12
|\| | | | | modfiy param generate & rewrite LSTM layer