Commit message (Collapse) | Author | Age | |
---|---|---|---|
* | doc change | TianxingHe | 2015-11-23 |
| | |||
* | add cflag __NERV_FUTURE_CUDA_7 | Determinant | 2015-11-23 |
| | |||
* | use consistent update calc; clean up code; no need for `direct_update` | Determinant | 2015-11-21 |
| | |||
* | Merge pull request #12 from cloudygoose/txh18/rnnlm | Ted Yin | 2015-11-18 |
|\ | | | | | add atomicAdd for cukernel | ||
| * | small coding style change | txh18 | 2015-11-18 |
| | | |||
| * | h300 and h400 worked well, log added | txh18 | 2015-11-18 |
| | | |||
| * | switch to kernel update | txh18 | 2015-11-17 |
| | | |||
| * | bug fix for select_linear layer-by-layer update | txh18 | 2015-11-17 |
| | | |||
| * | added atomicAdd for select_linear update, however, the result still seems ↵ | txh18 | 2015-11-17 |
| | | | | | | | | unreproducable, I changed select_linear layer update back to line-by-line | ||
| * | using atomicAdd for select_linear update | txh18 | 2015-11-17 |
| | | |||
| * | added small opt: use mmatrix in lm_trainer and reader | txh18 | 2015-11-17 |
| | | |||
| * | coding style change | txh18 | 2015-11-17 |
| | | |||
| * | added LOG-tnn-h400 LOG | txh18 | 2015-11-16 |
| | | |||
* | | Merge pull request #10 from cloudygoose/txh18/rnnlm | Ted Yin | 2015-11-16 |
|\| | | | | | add optimization for parameter update | ||
| * | change updateEI to update_by_err_input | txh18 | 2015-11-16 |
| | | |||
| * | coding style changes | txh18 | 2015-11-16 |
| | | |||
| * | changed the updates for affine layer, now just use update will be okay | txh18 | 2015-11-16 |
| |\ | | | | | | | | | | Merge branch 'txh18/rnnlm' | ||
| | * | unified param updates, now direct_update is the same speed with undirect_update | txh18 | 2015-11-16 |
| | | | |||
| | * | ... | txh18 | 2015-11-16 |
| | | | |||
| | * | ... | txh18 | 2015-11-16 |
| | | | |||
| | * | used os.clock() for timer | txh18 | 2015-11-16 |
| | | | |||
| | * | fixed direct update, did not know the result | txh18 | 2015-11-16 |
| | | | |||
| | * | added timer | txh18 | 2015-11-15 |
| | | | |||
| | * | merge lr schedule change | txh18 | 2015-11-15 |
| | |\ | | | | | | | | | | | | | Merge branch 'txh18/rnnlm' of github.com:Nerv-SJTU/nerv into txh18/rnnlm | ||
| | | * | got good PPL for H400... | cloudygoose | 2015-11-15 |
| | | | | |||
| | * | | added msr_sc set | txh18 | 2015-11-15 |
| | |/ | |||
| | * | small bug: lr_half | txh18 | 2015-11-13 |
| | | | |||
| | * | ... | txh18 | 2015-11-13 |
| | | | |||
| | * | added random seed | txh18 | 2015-11-13 |
| | | | |||
| | * | added loadstring | txh18 | 2015-11-13 |
| | | | |||
| | * | saving param file for every iter | txh18 | 2015-11-13 |
| | | | |||
| | * | change ppl_net to ppl_all | txh18 | 2015-11-13 |
| | | | |||
| | * | added wcost for select_linear layer | txh18 | 2015-11-12 |
| | | | |||
| | * | cleaning files... | txh18 | 2015-11-12 |
| | | | |||
| | * | get good PPL for h300, see m-tests/LOG-tnn-h300 | txh18 | 2015-11-12 |
| | | | |||
| | * | added a little debug info in reader | txh18 | 2015-11-11 |
| | | | |||
| | * | got good result when batch_size=1, strange! | txh18 | 2015-11-11 |
| | | | |||
| | * | bug fix : changed zero-filling across borders | txh18 | 2015-11-10 |
| | | | |||
| | * | small bug in lmseqreader | txh18 | 2015-11-09 |
| | | | |||
| | * | small bug about zeroing error | txh18 | 2015-11-09 |
| | | | |||
| | * | another bit error bug found | txh18 | 2015-11-09 |
| | | | |||
| | * | serious bug about bit operation in tnn | txh18 | 2015-11-08 |
| | | | |||
| | * | switched to softmax_ce_t | txh18 | 2015-11-08 |
| | | | |||
| | * | ih[0] nolonger zero | txh18 | 2015-11-08 |
| | | | |||
| | * | trying to test softmax_ce_t | txh18 | 2015-11-08 |
| | | | |||
| | * | meet a bug, don not know why | txh18 | 2015-11-07 |
| | | | |||
| | * | ready to test on ptb | txh18 | 2015-11-07 |
| | | | |||
| | * | writing the scheduler | txh18 | 2015-11-06 |
| | | | |||
| | * | added cross-border flush | txh18 | 2015-11-06 |
| | | | |||
| | * | first small tnn test seems to work | txh18 | 2015-11-06 |
| | | |