14253 Commits (a32d420043e50d3bcc8564d768584a9b1f40b5af)

Author	SHA1	Message	Date
Yan Xu	30568473ec	fix broadcast on mp mode (#15951) ... * fix broadcast with mp mode * polish code test=develop * fix bcast strategy test=develop * fic cpplint test=develop * fix py3 failed test=develop * fix comment test=develop * update comment test=develop	6 years ago
baojun	e3c37bd564	remove const_cast and refactor ngraph engine code (#15925) ... * remove concast_cast and refactor code test=develop * reduce flag use test=develop	6 years ago
chengduo	0979956619	Add memory profiler (#16137) ... test=develop	6 years ago
luotao1	b561ad1e55	Merge branch 'develop' into runtime_context	6 years ago
tink2123	61a6165c2c	modified api.spec ... test=develop	6 years ago
Zhen Wang	41b8cf0bae	Merge pull request #16162 from wzzju/fix_nan_static_quant ... Fix NaN bugs for static quantization strategy (mutil-cards train).	6 years ago
luotao1	fe78a92e6e	refine with comments ... test=develop	6 years ago
Zhen Wang	94b7c1ea7b	Merge pull request #16107 from wzzju/add_graph_clone ... Add clone function for IrGraph.	6 years ago
dengkaipeng	0ff9a403d0	fix format. test=develop	6 years ago
wopeizl	85709f4378	restore the exception caught since it is necessary for python call stack (#16160) ... test=develop	6 years ago
Zhen Wang	5420cf95f5	Merge pull request #16070 from wzzju/channel_wise_quant_op ... Add channel wise quant op and channel wise dequant op.	6 years ago
Zhen Wang	5685a48c23	Add some fixme. test=develop	6 years ago
dengkaipeng	b33e6bf5ef	remove comment code. test=develop	6 years ago
tink2123	eb09bd456a	modified api.spec ... test=develop	6 years ago
dengkaipeng	746740c41b	fix API.spec. test=develop	6 years ago
dengkaipeng	e4e3764060	use memory Copy. test=develop	6 years ago
dengkaipeng	d31693afec	no use _gt_score. test=develop	6 years ago
luotao1	5d20954ac4	add runtime shape for fuse_emb_seq_pool_grad ... test=develop	6 years ago
dengkaipeng	aad62eeca0	add doc for param default. test=develop	6 years ago
tink2123	a8e375d463	refine doc ... test=develop	6 years ago
dengkaipeng	585766acc0	fix spell mistake in doc. test=develop	6 years ago
dengkaipeng	b307533b7d	fix format. test=develop	6 years ago
dengkaipeng	afdf3c3f84	fix doc.test=develop	6 years ago
dengkaipeng	5b37cf0add	fix API.spec for yolov3_loss. test=develop	6 years ago
dengkaipeng	af4ef80e5b	fix API.spec not add defaults. test=develop	6 years ago
dengkaipeng	0d1a9996ac	fix unittest for yolov3_loss. test=develop	6 years ago
dengkaipeng	f0804433b0	add mixup score and label_smooth for yolov3_loss. test=develop	6 years ago
dengkaipeng	626fb859d9	add param default doc. test=develop	6 years ago
dengkaipeng	33c8607ef3	fix doc. test=develop	6 years ago
dengkaipeng	abb5a9c726	fix doc statement. test=develop	6 years ago
dengkaipeng	b399ee2a23	fix doc. test=develop	6 years ago
dengkaipeng	ad897304f9	fix pre-commit. test=develop	6 years ago
dengkaipeng	72a18bb160	add bbox range limit. test=develop	6 years ago
dengkaipeng	fb863b4820	add API.spec for yolo_box. test=develop	6 years ago
dengkaipeng	c9d4676bee	fix multi batch idx error. test=develop	6 years ago
dengkaipeng	7808f4c097	fix unittest for yolo_box_op. test=develop	6 years ago
dengkaipeng	cb2dca53c1	fix cuda kernel error	6 years ago
dengkaipeng	04b8b9e96c	add yolo_box_op CUDA kernel	6 years ago
dengkaipeng	452373decb	resize box in input image scale. test=develop	6 years ago
dengkaipeng	3896d955c7	add yolo_box_op CPU kernel	6 years ago
luotao1	8f6597aa0e	Merge branch 'develop' into infershape_example	6 years ago
sneaxiy	b26e9bd232	refine code ... test=develop	6 years ago
Zhen Wang	ac6ef06ffa	Add the Clone method in Graph. test=develop	6 years ago
Zhen Wang	01eddf125c	Not add graph copy construction method. test=develop	6 years ago
Zhen Wang	1b9c8d5f06	add clone function for IrGraph. test=develop	6 years ago
Tao Luo	ccc7c358b3	Merge pull request #16104 from tensor-tang/refine/jit ... refine jitkernels and test	6 years ago
Tao Luo	c49b7855fa	Merge pull request #16120 from Xreki/fix_cmake_compress ... Change the download and compress command of cmake.	6 years ago
Qiyang Min	1f4aa7a202	Imperative remove all descs (#16045) ... * Remove Desc in Forward Pass * Refactor VarBase * Add dbg info * Only check type in imperative mode * Polish code and support optimizer test=develop * Fix stop gradient problem in PyLayer test=develop	6 years ago
Zeng Jinle	472f16b5aa	Merge pull request #16063 from sneaxiy/enhance_gc ... Enhance gc	6 years ago
Tao Luo	e31f6e9831	Merge pull request #16146 from luotao1/zero_copy ... unify ZeroCopy in analysis_test	6 years ago
luotao1	31ccaf0916	add all_kernels_must_compute_runtime_shape example for speedup infershape ... test=develop	6 years ago
tensor-tang	14d871121b	enhance jitkernel unit test ... test=develop	6 years ago
Liu Yiqun	4e052e0ac9	Disable inference download for WIN32 temporary. ... test=develop	6 years ago
chengduo	ad80bde824	Revert "Revert "Add Event for TensorCopy"" (#16035) ... * Revert "Revert "Add Event for TensorCopy" (#16022)" This reverts commit e2da3a5b22. * use default stream test=develop	6 years ago
luotao1	1283833395	zero_copy tensor support INT32 ... test=develop	6 years ago
tensor-tang	cfc83c1445	refine jitcodekey and enhance unit tests ... test=develop	6 years ago
tensor-tang	6ff230a624	Merge remote-tracking branch 'ups/develop' into refine/jit	6 years ago
luotao1	31c4e1d9fc	Merge branch 'develop' into zero_copy	6 years ago
wopeizl	a38db3cb99	Fixrecordio (#16124) ... * fix recordio on win test=develop * test=develop * test=develop * fix code style test=develop * test=develop	6 years ago
sneaxiy	cfd012e2cb	add unittest ... test=develop	6 years ago
sneaxiy	d7407c90aa	refine cross_entropy mem ... test=develop	6 years ago
Cheerego	3c60446e59	fix deadlink (#16129) ... * fix deadlink fix https://github.com/PaddlePaddle/FluidDoc/issues/679 * test=develop * test=develop	6 years ago
luotao1	9e2c7e69fb	simplify the zero_copy tests ... test=develop	6 years ago
tink2123	cfc59b13e9	modified api.spec ... test=develop	6 years ago
sneaxiy	732fa00eaf	disable gc in recurrent_op currently ... test=develop	6 years ago
tink2123	e4e0d03459	fix format ... test=develop	6 years ago
Tink_Y	5579fae1d2	Update activation_op.cc ... test=develop	6 years ago
tensor-tang	45bdd84dac	enhance the jitkernel helper and add unit tests ... test=develop	6 years ago
tink2123	837ad7f86f	Add the inverse trigonometric function ... test=develop	6 years ago
ceci3	415d74a08e	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into npair_loss0	6 years ago
luotao1	aeee4cbe71	add compare between zerocopy and analysis	6 years ago
Liu Yiqun	6bb84b74b2	Change the download and compress command of cmake. ... test=develop	6 years ago
ceci3	3e0eb55515	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into npair_loss0 ... test = develop, update API.spec	6 years ago
tensor-tang	14a764c930	simplify the jitkernel templates and tests ... test=develop	6 years ago
ceci3	8b86c12e46	test=develop, update API.spec	6 years ago
Tao Luo	25ca2ca001	change init_idx to INT32 in transformer_test ... test=develop	6 years ago
ceci3	c8610739c3	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into npair_loss0	6 years ago
Yiqun Liu	66ead07ef9	Make parent_idx a dispensable output for beam_search op to support models saved by older paddle version. (#16106) ... test=develop	6 years ago
Yihua Xu	0a45441a84	Fix the node's order issue when the content of graph is changed (#16088) ... * Fix the node's sort issue when the graph is changed. test=develop * Clean code test=develop	6 years ago
nhzlx	2891070c66	cant not pass ci ... add if use static engine for trt test=develop	6 years ago
lidanqing	717bbc087b	Add INT32 support. INT32 in last switch case ... test=develop	6 years ago
nhzlx	93edcd773b	7 refine zero copy ... update trt in docker file test=develop	6 years ago
nhzlx	4b59646ed1	fix comments and fix cpplint ... test=develop	6 years ago
nhzlx	5863c86143	6. delete useless predictor id ... test=develop	6 years ago
nhzlx	f3d164faad	5. add static trt load model ... 1). add static trt load model 2). fix bug: when device_id is not 0, the trt will have a bug test=develop	6 years ago
nhzlx	31008100ba	4. do the trt_engine optim during init. ... add simple static mode loading test=develop	6 years ago
nhzlx	4f77248dd8	3. when runing in trt mode, do not allocate memory for parameters in fluid. ... test=develop	6 years ago
nhzlx	8c17190279	2. TRTEngine using stream only when execute.	6 years ago
nhzlx	88c24baa25	add static model load for trt ... 1. bind trt input and output to fluid tensors	6 years ago
Tao Luo	e5e7e9b865	Merge branch 'develop' into transformer_ut	6 years ago
Yiqun Liu	5bde120243	Make parent_idx a dispensable output for beam_search op to support models saved by older paddle version. (#16106) ... test=develop	6 years ago
Tao Luo	6f2581e4c5	Merge pull request #16090 from lidanqing-intel/paddle-int32 ... Add PaddleDType INT32 support	6 years ago
Yihua Xu	40f1dd818b	Fix the node's order issue when the content of graph is changed (#16088) ... * Fix the node's sort issue when the graph is changed. test=develop * Clean code test=develop	6 years ago
Zhaolong Xing	3d63aa0a11	Merge pull request #15729 from NHZlX/add_static_model_load_for_trt ... Four points for enhancing Paddle-TRT	6 years ago
jerrywgz	b0e3c02410	Merge pull request #15952 from jerrywgz/fpn_ops ... add distribute fpn proposals op, test=develop	6 years ago
tensor-tang	802f362ac4	unify the kernelfuncs cache and add unit test ... test=develop	6 years ago
nhzlx	a9ed427749	cant not pass ci ... add if use static engine for trt test=develop	6 years ago
Yiqun Liu	f31d515ce3	Enhance the op benchmark: (#16066) ... - Support setting attr in config - Support setting dtype and initializer for input in config test=develop	6 years ago
tensor-tang	2e7fea2b7f	polish the cast op doc (#16078) ... * polish the cast op doc test=develop * follow comments test=develop * fix api.spec test=develop	6 years ago
luotao1	fad06cb928	unify ZeroCopy in analysis_test	6 years ago
lidanqing	4aeb261da9	Add INT32 support. INT32 in last switch case ... test=develop	6 years ago
Yiqun Liu	36e2d3241e	Enhance the op benchmark: (#16066) ... - Support setting attr in config - Support setting dtype and initializer for input in config test=develop	6 years ago
tensor-tang	9be825a982	polish the cast op doc (#16078) ... * polish the cast op doc test=develop * follow comments test=develop * fix api.spec test=develop	6 years ago
jerrywgz	847bb6a279	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fpn_ops	6 years ago
Wu Yi	5e92eb3f25	add parallel graph dist test (#16076) ... * add parallel graph dist test=develop * update test=develop * update style test=develop	6 years ago
jerrywgz	e5759d6c38	refine doc, test=develop	6 years ago
jerrywgz	2b41743791	fix doc, test=develop	6 years ago
jerrywgz	c2eda2325b	refine code, test=develop	6 years ago
jerrywgz	9eb6d35f59	fix API.spec,test=develop	6 years ago
jerrywgz	a2e83d1d7b	add box_coder_and_assign, test=develop	6 years ago
Wu Yi	d206582337	add parallel graph dist test (#16076) ... * add parallel graph dist test=develop * update test=develop * update style test=develop	6 years ago
jerrywgz	893789a0d1	Merge pull request #16050 from jerrywgz/add_box_decoder_and_assign ... Add box decoder and assign	6 years ago
liuwei1031	1b5768c33b	fix a code bug which cause crash when empty variable is used, test=develop (#16080)	6 years ago
liuwei1031	045e5911bf	fix a code bug which cause crash when empty variable is used, test=develop (#16080)	6 years ago
ceci3	c109e6b3aa	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into npair_loss0	6 years ago
ceci3	7613918e23	test=develop, change labels name	6 years ago
xiaolil1	a177d48217	Add Requantize OP (#15318) ... * Enable INT8 ReQuantize OP test=develop * Clean code test=develop * Add comments test=develop * Revert "Clean code" test=develop This reverts commit a7a49b8aa214f9730cb84e11ea96da564fe4b4d9. * Modify requantize op test test=develop * fix requantize UT by moving public function to public test file. test=develop * Fix test fail due to file address change. test=develop * Change file address for requantize op. test=develop	6 years ago
chengduo	6fe7478ba8	Refine recurrent_op (#16027) ... * refine recurrent_op test=develop * remove unnecessary code test=develop	6 years ago
chengduo	f5a3751845	Refine recurrent_op (#16027) ... * refine recurrent_op test=develop * remove unnecessary code test=develop	6 years ago
sneaxiy	7b608396fe	fix travis-ci format check ... test=develop	6 years ago
ceci3	dc57952b7f	test=develop, add random to testfile	6 years ago
chengduo	84e3adbe60	Fix reshape bug (#16069) ... * In some case, the input may have one than one negative value. test=develop * fix matmul bug test=develop	6 years ago
wopeizl	eb367f990c	remove the ignored from is_empty and less_than test=develop (#15971) ... * remove the ignored from is_empty and less_than test=develop * fix api spec test=develop * fix the api spec test=develop * test=develop	6 years ago
liuwei1031	9cc6f4009f	add IfElse test case for ir memory optimize (#15998) ... * add ir memory optimize test case for IfElse op, test=develop * fix some unitttest failure by force using the python memory_optimize, test=develop * tweak comments, test=develop * fix unittest, test=develop * fix unittest, test=develop	6 years ago
luotao1	503efa8b86	refine SetCpuMathLibraryNumThreads ... test=develop	6 years ago
baojun	9f85876885	fix tanh typo test=develop (#16049)	6 years ago
whs	bd9669003f	Make sequence_erase op support for input with multi-level LoD. (#15982) ... test=develop	6 years ago
Tao Luo	1301dc1a27	remove legacy function in ExecutionContext ... test=develop	6 years ago
lidanqing	21156b8d4c	MKLDNN: Add UT for conv_transpose_mkldnn op. (#16030) ... * MKLDNN: Add UT for conv_transpose_mkldnn op. test=develop * MKLDNN: Add fuse_bias check UT for conv_transpose_mkldnn op. test=develop	6 years ago
dengkaipeng	b1a49e873f	fix statement. test=develop	6 years ago
dengkaipeng	0e0a2d046d	fix API.spec. test=develop	6 years ago
dengkaipeng	dbb8d07886	fix doc statement. test=develop	6 years ago
dengkaipeng	eeeebdd006	refine doc. test=develop	6 years ago
dengkaipeng	8ee866bf19	fix format. test=develop	6 years ago
dengkaipeng	9c47f36d1b	fix spectral_norm doc. test=develop	6 years ago
dengkaipeng	12416a24d2	add doc and test_layers. test=develop	6 years ago
dengkaipeng	63d322f07c	fix attr dim calc. test=develop	6 years ago
dengkaipeng	ca1502c7f5	add grad kernel for spectral_norm. test=develop	6 years ago
dengkaipeng	8956a59637	add unittest for spectral_norm. test=develop	6 years ago
dengkaipeng	fd66089d23	add spectral_norm forwarn kenel	6 years ago
tensor-tang	cab46b62f8	refine vbroadcast jitcode ... test=develop	6 years ago
tensor-tang	6010361c7a	add vbroadcast mkl code and jitcode ... test=develop	6 years ago
tensor-tang	2e96da453a	add vbroadcast jitkernel refer code and use it ... test=develop	6 years ago
tensor-tang	020540948f	add jitkernel vcopy and speedup unit test time ... test=develop	6 years ago
tensor-tang	6057f36208	Merge pull request #15996 from tensor-tang/op/embgrad ... refine embeddingseqpool grad	6 years ago
chengduo	c67afb0f76	Fix reshape bug (#16069) ... * In some case, the input may have one than one negative value. test=develop * fix matmul bug test=develop	6 years ago
Tao Luo	14b4337663	Merge pull request #16062 from luotao1/num_threads ... refine SetCpuMathLibraryNumThreads	6 years ago
sneaxiy	33138a421d	remove match check ... test=develop	6 years ago
wopeizl	7fbf52daa3	remove the ignored from is_empty and less_than test=develop (#15971) ... * remove the ignored from is_empty and less_than test=develop * fix api spec test=develop * fix the api spec test=develop * test=develop	6 years ago
Zhen Wang	8063b31e2d	Reduce redundant code for channel wise dequant op. test=develop	6 years ago