| Commit message (Expand) | Author | Age |
|---|
| * | add layers from `layersT/` to `layer/` | Determinant | 2016-02-21 |
| * | generalize softmax_ce.lua (to softmax_ce_t.lua) | Determinant | 2016-02-18 |
| * | ...tnn | Determinant | 2016-02-17 |
| * | Merge branch 'txh18/rnnlm' of github.com:cloudygoose/nerv into tnn | Determinant | 2016-02-17 |
| |\ |
|
| | * | bug fixes in lm_sampler | txh18 | 2016-02-06 |
| | * | ... | txh18 | 2016-02-05 |
| | * | 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 |
| | * | new changes to select_gpu | txh18 | 2016-01-31 |
| | * | 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 |
| | * | the prefixsum_row operation of matrix is implemented | txh18 | 2016-01-20 |
| * | | try to merge manually | Determinant | 2016-02-17 |
| * | | fixed some minor problem | txh18 | 2016-02-16 |
| * | | ... | Determinant | 2016-02-16 |
| * | | improve parameter auto-detection | Determinant | 2016-02-16 |
| * | | pass cflags to nvcc correctly; add omitted func decl | Determinant | 2016-02-16 |
| * | | move curand_gen out of the matrix layout | Determinant | 2016-02-15 |
| * | | try a basic merge | Determinant | 2016-02-15 |
| * | | Merge pull request #21 from cloudygoose/txh18/rnnlm | TianxingHe | 2016-01-19 |
| |\| |
|
| | * | 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 |
| | * | small bug fix in tnn | txh18 | 2015-12-29 |
| | * | small bug fix in tnn | txh18 | 2015-12-29 |
| | * | small change in tnn, will create all sub-layers first | txh18 | 2015-12-29 |
| | * | Merge branch 'txh18/rnnlm' of github.com:cloudygoose/nerv into txh18/rnnlm | txh18 | 2015-12-29 |
| | |\ |
|
| | | * | try whole vocab for twitter | cloudygoose | 2015-12-28 |
| | * | | Merge branch 'txh18/rnnlm' of github.com:cloudygoose/nerv into txh18/rnnlm | txh18 | 2015-12-28 |
| | |\| |
|
| | | * | added unk_cn to LMResult | cloudygoose | 2015-12-28 |
| | * | | ... | txh18 | 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 |