aboutsummaryrefslogtreecommitdiff
Commit message (Expand)AuthorAge
* bug fixes in lm_samplertxh182016-02-06
* ...txh182016-02-05
* enhanced m-test/lm_sampletxh182016-02-05
* ..txh182016-02-05
* ...txh182016-02-05
* made lm sampling code cleanertxh182016-02-05
* added same_io option to lm_seq_readertxh182016-02-03
* new changes to select_gputxh182016-01-31
* like data of twitter from choose2 to choosetxh182016-01-30
* select gpu code from mfytxh182016-01-29
* moved gru_t to tnn/layersTtxh182016-01-29
* added logp addition to LMResulttxh182016-01-27
* tiny bug fix in LMVocabtxh182016-01-21
* used prefixsum_row operation to speed up sampling on the softmax outputtxh182016-01-20
* the prefixsum_row operation of matrix is implementedtxh182016-01-20
* big fixes about lm_samplertxh182016-01-19
* added lm_sampler, todo:test ittxh182016-01-19
* developing sample_grulmtxh182016-01-18
* added bigrulm_ptb_main.luatxh182016-01-13
* ...txh182016-01-12
* added wordprob into gru_ptb_main.luatxh182016-01-11
* added word_prob feature to lm_trainertxh182016-01-06
* ...txh182016-01-01
* small bug fix in tnntxh182015-12-29
* small bug fix in tnntxh182015-12-29
* small change in tnn, will create all sub-layers firsttxh182015-12-29
* Merge branch 'txh18/rnnlm' of github.com:cloudygoose/nerv into txh18/rnnlmtxh182015-12-29
|\
| * try whole vocab for twittercloudygoose2015-12-28
* | Merge branch 'txh18/rnnlm' of github.com:cloudygoose/nerv into txh18/rnnlmtxh182015-12-28
|\|
| * added unk_cn to LMResultcloudygoose2015-12-28
* | ...txh182015-12-28
|/
* revised twitter set for grulmcloudygoose2015-12-28
* ...txh182015-12-25
* speedup testout in lm_trainertxh182015-12-25
* ...txh182015-12-25
* the grulm baseline seems to work finetxh182015-12-25
* trying to find a fimpler lstm_v2, then aborttxh182015-12-24
* get a new log for rnnlm_h300txh182015-12-23
* changed affine_recurrent used in lm to affine_recurrent_plusvectxh182015-12-23
* added copy_rows_fromd_by_colidx for clearer namingtxh182015-12-22
* ...txh182015-12-22
* give a update_select_rows a more proper nametxh182015-12-22
* added a garbace collect in tnntxh182015-12-21
* added compressed_label support in the readertxh182015-12-21
* small mistake in layersTtxh182015-12-20
* added find_param method for layersTtxh182015-12-20
* bug fix in lmptb.vocabtxh182015-12-13
* ...txh182015-12-13
* move lmvocab:read_line to lmutiltxh182015-12-13
* bug fix: added check in the select_linear kerneltxh182015-12-11