Yu Yang
|
11c8ab80ec
|
Revert unchanged files
|
8 years ago |
|
Yu Yang
|
3f1151a54c
|
Add error clipping to MT demo.
* Compose GRU step naive layer in trainer config helpers.
* It is uses mixed_layer for gate.
* It supports ERROR_CLIPPING, DROPOUT
* Add error clipping in MT demo.
* Fix #1143
* Fix #1891
|
8 years ago |
Luo Tao
|
555b2dfdad
|
add seqtext_print for seqToseq demo
|
8 years ago |
|
Luo Tao
|
a42233c2c2
|
add wmt14 trg_dict
|
8 years ago |
qiaolongfei
|
b669b5fc30
|
fix style problem
|
8 years ago |
|
qiaolongfei
|
07a8f0ef6b
|
refine code, remove beam_search.py
|
8 years ago |
|
qiaolongfei
|
ba51e6ea68
|
fix style problem
|
8 years ago |
|
qiaolongfei
|
42e9d7c004
|
restore old code of seqToseq_net
|
8 years ago |
|
qiaolongfei
|
a4a599ab23
|
refine code, remove duplicate code between layer and with_extra_parent_layer
|
8 years ago |
|
qiaolongfei
|
ea8013e48f
|
can run test.py for generating
|
8 years ago |
|
qiaolongfei
|
06690cfb01
|
add l2 regularization to reduce the probability of fpe exception
|
8 years ago |
|
qiaolongfei
|
2ad9fd646f
|
revert preprocess.py
|
8 years ago |
|
qiaolongfei
|
3780679203
|
fix conflict
|
8 years ago |
|
Yu Yang
|
26445368a2
|
Rename reader_dict to feeding
* Also fix some other bugs.
* Fix #1495
|
8 years ago |
|
qiaolongfei
|
f6f444ff3d
|
optimize code
|
8 years ago |
|
qiaolongfei
|
98522dcb33
|
optimizer wmt14 dataset
|
8 years ago |
|
qiaolongfei
|
8fa09b82f9
|
add some comment for api_train_v2 of seqtoseq
|
8 years ago |
|
qiaolongfei
|
c5fb4fd4d0
|
optimize import of eqToseq_net_v2 for book
|
8 years ago |
|
qiaolongfei
|
a6364f9e6a
|
change batch_size to 5
|
8 years ago |
|
qiaolongfei
|
e60d94b3d8
|
correct data_type
|
8 years ago |
|
qiaolongfei
|
495861f559
|
add v2 demo to seqtoseq, fix __dfs_travel__ for v2 layers
|
8 years ago |
zhouyingfeng
|
6c4831a096
|
add "paddle usage" scripts in all demos
resolve #965
|
8 years ago |
Yi Wang
|
e9549cbb78
|
Change "Baidu, Inc" into "PaddlePaddle Authors"
|
8 years ago |
|
Luo Tao
|
16bebc4388
|
some tiny fix
|
8 years ago |
|
Luo Tao
|
11b7625d48
|
use dictionary comprehension to pythonic code
|
8 years ago |
|
Luo Tao
|
8ac9e9a8dc
|
fix protobuf size limit of seq2seq demo
|
8 years ago |
|
Yu Yang
|
c9c60a1588
|
Change demo datafile location by using CDN in baidu.
|
9 years ago |
qijun
|
319742c641
|
format python code in demo, doc, doc_cn and paddle directories
|
9 years ago |
|
luotao1
|
91df606280
|
remove some copyfrom in AgentLayer and ExpandLayer, fix warning in seq2seq config (#183)
|
9 years ago |
|
luotao1
|
4615c5172c
|
beam search api and unitest in hierarchical rnn (#122)
|
9 years ago |
|
Luo Tao
|
d2e1b46f24
|
update beam_search and seqToseq config, and add ExpActivation api
|
9 years ago |
wangjiang03
|
4132702362
|
Add RNN Tutorial.
ISSUE=4589755
git-svn-id: https://svn.baidu.com/idl/trunk/paddle@1442 1ad973e4-5ce8-4261-8a94-b56d1f490c56
|
9 years ago |
caoying03
|
af724aa6c7
|
add comments for beam search in config helpers.
ISSUE=4599577
git-svn-id: https://svn.baidu.com/idl/trunk/paddle@1440 1ad973e4-5ce8-4261-8a94-b56d1f490c56
|
9 years ago |
luotao02
|
3e87021df1
|
refine demo dataprovider and some tiny fix
ISSUE=4597359
git-svn-id: https://svn.baidu.com/idl/trunk/paddle@1432 1ad973e4-5ce8-4261-8a94-b56d1f490c56
|
9 years ago |
zhangjinchao01
|
b72beee4f0
|
fix dash and space bug,
ISSUE=4586495
git-svn-id: https://svn.baidu.com/idl/trunk/paddle@1408 1ad973e4-5ce8-4261-8a94-b56d1f490c56
|
9 years ago |
