Commits · f784b9099e03c37ef11692cbd63ff3252c716dc9 · Emmay / NiuTrans.Tensor · GitLab

26 Dec, 2018 2 commits
- implement sum broadcasting by unsqueezing · f784b909
  xiaotong committed Dec 26, 2018
  
  f784b909 Browse Files
- add broadcasting · 6ba61279
  xiaotong committed Dec 26, 2018
  
  6ba61279 Browse Files
25 Dec, 2018 1 commit
- remove -smallfootprint and keep the net as small as possible by default · 947db8fb
  xiaotong committed Dec 25, 2018
  
  947db8fb Browse Files
24 Dec, 2018 2 commits
- 1. fixed the bug in the Spread function. 2. add compare and OnehotAndIndex… · 854a4835
```
1. fixed the bug in the Spread function.  2. add compare and OnehotAndIndex function 3. optimize the code
```
  xuchen committed Dec 24, 2018
  854a4835 Browse Files
- introduce small-footprint backward computation (by using "-smallfootprint") · 61c4d15c
  xiaotong committed Dec 24, 2018
  
  61c4d15c Browse Files
18 Dec, 2018 1 commit
- replace XLink::ShowNetwork with XNet::SHowNetwork · f8c57160
  xiaotong committed Dec 18, 2018
  
  f8c57160 Browse Files
13 Dec, 2018 1 commit
- add a start position for setdata · 31d989e9
  xiaotong committed Dec 13, 2018
  
  31d989e9 Browse Files
09 Dec, 2018 1 commit
- generate masks for t2t mt models · 3e7f7645
  xiaotong committed Dec 09, 2018
  
  3e7f7645 Browse Files
07 Dec, 2018 2 commits
- softmax output -> logsoftmax output · 21892dbf
  xiaotong committed Dec 07, 2018
  
  21892dbf Browse Files
- rewrite reducesumall · 8f2d16f5
  xiaotong committed Dec 07, 2018
  
  8f2d16f5 Browse Files
04 Dec, 2018 1 commit
- fix the bug of suming the word numbers of both source and target-sides for the… · 9b0d4df8
```
fix the bug of suming the word numbers of both source and target-sides for the loss computation in transformer MT models
```
  xiaotong committed Dec 04, 2018
  9b0d4df8 Browse Files
03 Dec, 2018 1 commit
- better control of the strategy of the merge method · 1c26ff5b
  xiaotong committed Dec 03, 2018
  
  1c26ff5b Browse Files
29 Nov, 2018 1 commit
- revise the comment · 78954fad
  xiaotong committed Nov 29, 2018
  
  78954fad Browse Files
28 Nov, 2018 8 commits
- clean useless code · dc56fd67
  xiaotong committed Nov 28, 2018
  
  dc56fd67 Browse Files
- recover the Main.cpp file · 49869ae5
  xuchen committed Nov 28, 2018
  
  49869ae5 Browse Files
- optimize the implementation of LoadBatchMT · 126c581f
  xuchen committed Nov 28, 2018
  
  126c581f Browse Files
- cpu implementation of the gather and spread function · b3fa7a37
  xuchen committed Nov 28, 2018
  
  b3fa7a37 Browse Files
- improve the implementation of gather and spread · 2fea6615
  xuchen committed Nov 28, 2018
  
  2fea6615 Browse Files
- replace the cuda thread allocation code · 99225c29
  xiaotong committed Nov 28, 2018
  
  99225c29 Browse Files
- remove commented lines · 58abfba4
  xiaotong committed Nov 28, 2018
  
  58abfba4 Browse Files
- better memory allocation · 4cabf059
  xiaotong committed Nov 28, 2018
  
  4cabf059 Browse Files
27 Nov, 2018 1 commit
- correct unsafe code · cf149d57
  xiaotong committed Nov 27, 2018
  
  cf149d57 Browse Files
26 Nov, 2018 3 commits
- formatting · 5546a260
  xiaotong committed Nov 26, 2018
  
  5546a260 Browse Files
- new interfaces of CopyIndexed · d8bd1ef2
  xiaotong committed Nov 26, 2018
  
  d8bd1ef2 Browse Files
- fix a bug of memory leak · 7c44bfd2
  xiaotong committed Nov 26, 2018
  
  7c44bfd2 Browse Files
25 Nov, 2018 1 commit
- speed-up data fetching · ce92843d
  xiaotong committed Nov 25, 2018
  
  ce92843d Browse Files
23 Nov, 2018 1 commit
- improve the implementation of Unsqueeze · 229db8c6
  xiaotong committed Nov 23, 2018
  
  229db8c6 Browse Files
22 Nov, 2018 1 commit
- fix the bug of invalid memory pointer in releasing a memory pool · fe90b454
  xiaotong committed Nov 22, 2018
  
  fe90b454 Browse Files
21 Nov, 2018 3 commits
- new comment · 48661938
  xiaotong committed Nov 21, 2018
  
  48661938 Browse Files
- improve the implementation of _CudaSpreadForGather · 314a02af
  xiaotong committed Nov 21, 2018
  
  314a02af Browse Files
- improve the code of _CudaBLASMatrixMULList · 8f665e61
  xiaotong committed Nov 21, 2018
  
  8f665e61 Browse Files
19 Nov, 2018 3 commits
- remove some code · ac620226
  xiaotong committed Nov 19, 2018
  
  ac620226 Browse Files
- Merge branch 'xuchen' into xiaotong-working · 80ab70a2
  xuchen committed Nov 19, 2018
  
  80ab70a2 Browse Files
- restore the previous implemention · b83a6798
  xuchen committed Nov 19, 2018
  
  b83a6798 Browse Files
18 Nov, 2018 1 commit
- use smaller batches for training · 411cff4c
  xiaotong committed Nov 18, 2018
  
  411cff4c Browse Files
17 Nov, 2018 1 commit
- remove model dumping · 383759ae
  xiaotong committed Nov 17, 2018
  
  383759ae Browse Files
16 Nov, 2018 2 commits
- move the hard dump of model · af3acf68
  xiaotong committed Nov 16, 2018
  
  af3acf68 Browse Files
- correct the bug of loading samples for Tranformer training · 78339123
  xiaotong committed Nov 16, 2018
  
  78339123 Browse Files
15 Nov, 2018 2 commits
- reduce memory footprint for XMem · ca343382
  xiaotong committed Nov 15, 2018
  
  ca343382 Browse Files
- debugging · 12f84346
  xiaotong committed Nov 15, 2018
  
  12f84346 Browse Files