m53297601
/
Paddle
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
11385 Commits
277 Branches
51 Tags
204 MiB
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from '4ca19d4e18'
${ noResults }
Commit Graph

29 Commits (4ca19d4e18c73cd84e1787a79704f2a1da3c8c0a)

Author SHA1 Message Date
ying 7210d0fa95 follow comments.
8 years ago
ying d00eb53a93 add linear projection to q, k and v.
8 years ago
ying 0d96899f18 fix the documentation.
8 years ago
ying d163592a3f Merge branch 'develop' into multihead_attention
8 years ago
ying 9396c6d927 fix bugs.
8 years ago
whs d8b923ab04
Merge pull request #7777 from wanghaoshuang/fix_conv_group
8 years ago
ying 3be6c736f6 add multihead_attention.
8 years ago
wanghaoshuang c0ed2e4157 Change 0 to 0.0
8 years ago
wanghaoshuang ee21f2f601 Change default value of drop_rate in img_conv_group to 0
8 years ago
ying dace68ac6d Merge branch 'develop' into multihead_attention
8 years ago
ying 113cd6b31c add multi-head scaled_dot_product attention.
8 years ago
ying 3e195d86d8 add wrapper for multihead_attention.
8 years ago
dzhwinter e983cc90fc
"fix decode bug" (#7711)
8 years ago
chengduoZH edd2132679 remove conflict
8 years ago
guosheng db959d6350 Add dot_product_attention to nets.__all__
8 years ago
guosheng 66054984cd Merge branch 'develop' of https://github.com/PaddlePaddle/paddle into add-dot_product_attention
8 years ago
guosheng 9bcb2d268e Add python wrapper for matmul_op and dot_product_attention
8 years ago
chengduoZH 24f528a1a5 follow comments
8 years ago
dzhwinter b9b75377a2
Feature/hooks (#7513)
8 years ago
chengduoZH 251c6032fb set use_cudnn as default
8 years ago
chengduoZH 78dc93430c expose use_cudnn
8 years ago
guosheng f2e1f3e114 Fix activation for glu
8 years ago
guosheng ef129718ea Merge branch 'develop' of https://github.com/PaddlePaddle/paddle into add-python-glu
8 years ago
guosheng c083a60d7a Add python split and glu
8 years ago
ying 8ac744f372 add wrapper for elementwise math operator.
8 years ago
Yu Yang 7901f06ab7
Remove `main_program` and `startup_program` as the paramter of layer function (#6655)
8 years ago
fengjiayi 8f7d0b1814
add param_attr for nets (#6509)
8 years ago
Yu Yang 0ac8c74e63
Unify fluid submodules to fluid module (#5924)
8 years ago
Qiao Longfei 4adc8a7aa1
Change framework to fluid (#5637)
8 years ago