23 Commits (6b9f1d343eac40d71b5275071a9e47a04546a356)

Author	SHA1	Message	Date
guosheng	6b9f1d343e	Make weight normalization adapt to the up-to-date code	7 years ago
guosheng	a422f34607	Merge branch 'develop' of https://github.com/PaddlePaddle/paddle into add-weight-normalization	7 years ago
guosheng	e27a030072	Add weight normalization	7 years ago
whs	bac401cd51	Merge pull request #7812 from wanghaoshuang/fix_layer_helper ... Deepcopy ParamAttr while creating parameter.	7 years ago
wanghaoshuang	00ab68ca88	Deepcopy ParamAttr while creating parameter.	7 years ago
Qiao Longfei	e7d44a2034	Nmt model (#7340) ... neural machine translation model support beam search with while op	7 years ago
dzhwinter	e983cc90fc	"fix decode bug" (#7711) ... * "fix decode bug" * "follow commnet" * "fix error" * "fix hook bug" * fix based comment * fix copyright * fix based on comment	7 years ago
dzhwinter	b9b75377a2	Feature/hooks (#7513) ... * add copyright hook * add copyright hook * refine copyright hook * "test copyright hook" * fix check style * fix ci	7 years ago
QI JUN	fe341bacde	refine batch norm python layer (#7348)	7 years ago
fengjiayi	874cac0c94	Change softmax	7 years ago
Yang Yu	b23982a2de	Add ReorderLoDTensorByRank ... It is useful to reorder RNN memory block.	7 years ago
Yu Yang	7901f06ab7	Remove `main_program` and `startup_program` as the paramter of layer function (#6655) ... * Simplize system_allocator and fix GPU_INFO * Remove main_program/startup_program * Fix optimizer * Fix CI * Follow comments	7 years ago
Yu Yang	229c2e7883	Feature/while op sentiment analysis (#6282) ... * Add DataFeeder A v2 API like data feeder for book demos. We can feed data directly from reader. * Fix CI * Add an unittest for while/rnn op forward * Add unittest for raw while op backward * Fix CI * Complete Dynamic RNN	7 years ago
Qiao Longfei	45c8a88a3e	add crf_decoding layer (#6274) ... * add crf_decoding layer * fix some typo * fix test_crf_decoding_op	7 years ago
Yu Yang	1b6dcc2fe8	Feature/param attr (#5996) ... * Make param_attr as a strong typed class Fix #5819	7 years ago
Yu Yang	0aceeee1fa	Feature/remove g program (#5930) ... * Unify fluid submodules to fluid module Change books just use `import fluid`, not submodules * Remove g_main_program/g_startup_program Use default_main_program/default_startup_program instead * Typo * Fix CI	7 years ago
Yu Yang	0ac8c74e63	Unify fluid submodules to fluid module (#5924) ... Change books just use `import fluid`, not submodules	7 years ago
fengjiayi	50d670ee06	Unify dtype and datatype (#5869) ... * Change all `data_type` in Python to `dtype` * Change `date_type` in C++ to `dtype` * Refine	8 years ago
Qiao Longfei	53bd51e3f4	07/Label semantic roles (#5798) ... * init label_semantic_roles.py * add linear_chain_crf and test * complete test_linear_chain_crf * correct last layer of db_lstm * update optimizer and initializer * update param_initializer of embedding_layer * support load pre trained embedding * rm unused parameter * optimize code * clean code * fix test * add todo	8 years ago
Abhinav Arora	e930f49673	Improve the initializer Interface for fc, sequence_conv and conv2d layers (#5760) ... * Improve the initializer Interface for fc, sequence_conv and conv2d layers * Fix some typos in python code * Fix CI	8 years ago
xuwei06	81bb26f3bd	Removing debug print and moving assert	8 years ago
xuwei06	a5c9e6ace2	Fix conv2d bias ... The size of the bias parameter should be the number of filters.	8 years ago
Qiao Longfei	4adc8a7aa1	Change framework to fluid (#5637) ... * init commit * change some dir name	8 years ago