Paddle

Commit Graph

Author	SHA1	Message	Date
Yu Yang	894236a128	Merge pull request #6730 from tonyyang-svail/parallel_do [WIP]: feature/parallel_do	9 years ago
dzhwinter	5593858dd9	Feature/use cudnn (#7141 ) * "add c++ side kernel selection" * "add multiple kernel op test" * "kernel selection only support cudnn" * "better formatter" * "small fix with UseCPU" * "depends on change interface Get(Place, Library)" * "fix CI" * "fix python cudnn test" * "leave the register cudnn op to another PR" * "fix CI" * "use all kernel by default" * "fix CI"	9 years ago
Yang Yang	9313233297	merge develop	9 years ago
fengjiayi	b775b6cbaa	Merge pull request #6741 from JiayiFeng/dev_new_backward [WIP] new backward	9 years ago
typhoonzero	1cb9635947	fix dist train trainspiler bugs	9 years ago
fengjiayi	febb725102	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into dev_new_backward	9 years ago
Qiao Longfei	af0c4c45a3	Impl kernel hint (#6883 ) * init kernel hint * fix typo * rm unused code * add include in op_kernel.h * restore op_kernel since it will be moved to op_kernel_type * change force_cpu to use_cpu * fix compilation	9 years ago
Yu Yang	ca82fd2565	Merge pull request #6789 from reyoung/feature/add_reorder_lod_tensor Add ReorderLoDTensorByRank	9 years ago
typhoonzero	175a4f52c2	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into simple_dist_train_api	9 years ago
typhoonzero	4658f9501e	fix delete ops	9 years ago
Yang Yu	b23982a2de	Add ReorderLoDTensorByRank It is useful to reorder RNN memory block.	9 years ago
Qiao Longfei	d639b13f15	Merge pull request #6744 from jacquesqiao/expose-const-value Expose const value	9 years ago
Yang Yang	2f56d4b3d4	forward pass compile time	9 years ago
qiaolongfei	5c530ea827	export const value to python	9 years ago
Yu Yang	de85470d78	Support Clip in param_attr (#6729 ) * Support Clip in param_attr * Fix the order of clip & regular Regular is not need to be clipped	9 years ago
fengjiayi	f2e76008d3	update	9 years ago
typhoonzero	2b47fb3d25	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into simple_dist_train_api	9 years ago
typhoonzero	b4cd7f3d75	wip need ut	9 years ago
typhoonzero	308491a94a	update for simple dist train	9 years ago
Yu Yang	584c9cfc82	Add comments of unique_name, Variable, Operator (#6342 )	9 years ago
typhoonzero	dd46d95fe4	wip	9 years ago
dzhwinter	4eac85c60b	"add init seed" (#6221 ) * "add init seed" * "fix compile error" * "add program level seed setting" * "fixed based on comments"	9 years ago
Qiao Longfei	45c8a88a3e	add crf_decoding layer (#6274 ) * add crf_decoding layer * fix some typo * fix test_crf_decoding_op	9 years ago
Yu Yang	ac596a3952	Feature/switch program (#5932 ) * 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 * Add API for switch default program * Two functions: switch_main_program/switch_startup_program * A guard: program_guard. Users can use the `with` statement change default programs * Change unittests in `test_layers` * Fix CI * Fix CI * Fix CI	9 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	9 years ago
Yu Yang	d89ff5b614	Restore the param infos in Program.clone() (#5873 ) * Restore the param infos in Program.clone() The Program.clone only clone the variables and ops in the program into a new program. However, the information of Parameter is not clone. So we need restore the information of Parameters. Fix #5871 * Follow comments * Fix CI * Fix CI * Fix CI	9 years ago
Yu Yang	0ac8c74e63	Unify fluid submodules to fluid module (#5924 ) Change books just use `import fluid`, not submodules	9 years ago
QI JUN	3a76062c84	support testing when training and handle dropout and batch_norm operator in testing mode (#5734 ) * is_training to is_test in dropout op * handle dropout and batch_norm operator when prune pdesc in testing mode * handle dropout and batch_norm operator when prune pdesc in testing mode * add get_inference_program method * fix dropout op * fix ci * test data after each batch training * refine code * refine test_book3 * fix ci * follow comments	9 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	9 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	9 years ago
fengjiayi	044d671e73	Rename 'argu' in framework.py to 'arg' (#5723 )	9 years ago
Yang Yang(Tony)	18f0c40a97	feature/while_grad_op (#5554 ) * first commit * Python API for while op * Python Unittest for simple while_op forward * fix out to be list * Fix UT * VarType * Fix several bugs * Fix bug * Fix bug * Fix Bug * Fix bug * Fix unittest * Remove debug log * Add comments * add PADDLE_ENFORCE * while_grad_op first commit * Add `BlockDescBind::FindRecursiveOrCreateVar()` and fix bugs * not sure how to setdim of while outputs * push for test * add executor vlog * fix bug of while_op cond * Several enhancement for code 1. Backward always infer shape & infer var type. Since there are RENAME variables will be created when creating backward operator, but their shape & var types are not inferenced. 2. Never use SomePtr-> directly, since every pointer could be nullptr if it is a function return value. Add `detail::Ref` to cast pointer to reference safely. 3. Enhance error message for backward. 4. Infer data type of variable in `sum` and `tensor_write` * Fix bugs of while_op gradient * Fix several bugs of while_op grad * fix fill zeros like * fix 3 >= 3 * fix place holder shouldn't be null * fail on sum op * Fix SumOp of TensorList * clean up * pass while test * fix test_array_write_read * pass sum op * Support int/int64 for fill_constant_batch_size_like * Fix compile	9 years ago
Helin Wang	3157ce6123	Simpily demo, add paddle.default_main_program() and paddle.default_startup_program - Removed all main_program and startup_program in the demo. - Using paddle.default_main_program() hides the implementation detail (e.g., using g_main_program) from the user, we can change the implementation in the future much easier.	9 years ago
Qiao Longfei	4adc8a7aa1	Change framework to fluid (#5637 ) * init commit * change some dir name	9 years ago

34 Commits (4a3580ac751fdfdba52575d83ef151bed75b0396)