11061 Commits (d26e4507dac94e0de3a24816541f06082770bc35)

Author	SHA1	Message	Date
Sylwester Fraczek	55d6950a1a	rewrite conv_bn fuse pass to eigen ... test=develop	7 years ago
chengduo	9c77b65c06	Fix layers.uniform_random (#13823) ... * fix layers.uniform_random * fix uniform_random test=develop * remove var type set test=develop * fix similar error test=develop	7 years ago
nhzlx	320c78e16f	fix commets ... test=develop	7 years ago
Yibing Liu	cbe4292516	Add sequence unpad op ... test=develop	7 years ago
tensor-tang	bcb8ea397d	Merge remote-tracking branch 'ups/develop' into fea/jitkernel_peephole ... test=develop	7 years ago
tensor-tang	8e182170ba	refine and replace lstm peephole kernel	7 years ago
nhzlx	efa5bac7ad	fix demo_ci bug in vis_demo.cc ... test=develop	7 years ago
tensor-tang	dc5a7b906d	fix default number of threads when inference with or without MKLDNN ... test=develop	7 years ago
Xin Pan	228506618b	Avoid GetMutable implicitly reset Var Type. ... This can cause a lot of problem: 1. Wrong operator implementation, Op can get a wrong type without failure. 2. Anytype can be Get without defined in VarType. Also fix wrong STEP_SCOPE usage. test=develop	7 years ago
Dun	5f2e837847	optimize depthwise conv by register memory (#13778) ... * optimize depthwise conv by register memory * test=develop	7 years ago
minqiyang	3f6ec90060	Polish code ... test=develop	7 years ago
minqiyang	9878eedbaa	Change API.spec ... test=develop	7 years ago
Qiao Longfei	5428cb9908	Profiler support merge data of all thread (#13811) ... * profiler infor merge thread statistic information * update profiler * fix bug * add merge thread msg to report * optimize report * statistic the time of ops in each thread but not all * optimize report format * optimize profile report * optimize profile report test=develop	7 years ago
nhzlx	bf7a2789a0	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into add_trt_pad_op ... test=develop	7 years ago
nhzlx	0cb88c34be	add op converter	7 years ago
tensor-tang	7ef2699e18	init peephole runtime kernel	7 years ago
Qiyang Min	f99ea99e36	Merge pull request #13720 from velconia/fix_grad_clip ... Merge selected_rows for clip_by_norm op	7 years ago
minqiyang	f40848828d	Polish code ... test=develop	7 years ago
minqiyang	e2e82bde32	Accelerate Reshape op	7 years ago
minqiyang	0385b0a1ea	Accelerate SequencePool Op on SUM mode ... test=develop	7 years ago
minqiyang	8ec748cfa0	Accelerate SelectedRows Functors: ... 1. Accelerate SelectedRows MergeAdd functor 2. Add SelectedRowsSumTo functor to support MergeAdd multiple SelectedRows into one test=develop	7 years ago
Xin Pan	63b2e98f3d	Explain LoD and a few other concepts ... test=develop	7 years ago
Tao Luo	9b11a17502	Revert "[MKLDNN] Pass: Fuse Conv + Bias"	7 years ago
Tao Luo	ce248a15d9	Merge pull request #13368 from Sand3r-/mgallus/conv-bias-pass ... [MKLDNN] Pass: Fuse Conv + Bias	7 years ago
whs	7e651c8641	Fix truncated norm (#13785) ... * Fix truncated normal. * test=develop	7 years ago
Tao Luo	16b1beb244	Merge pull request #13486 from sfraczek/sfraczek/conv-bn-fuse-pass ... Sfraczek/conv bn fuse pass	7 years ago
Zhaolong Xing	5d5587fff7	Merge pull request #13792 from NHZlX/trt_dy_lib ... add trt api lib to paddle_fluid lib	7 years ago
Michal Gallus	40b17be4b0	Pass: Fuse Conv + Bias ... test=develop	7 years ago
minqiyang	1456b8ec7d	Add unittest for clip_by_norm_op with SelectedRows ... test=develop	7 years ago
Tao Luo	fd0dd07ab4	Merge pull request #13726 from jczaja/prv-fused_embedding_fc_lstm-ut ... Unit test to Fused_embedding_fc_lstm op	7 years ago
Sylwester Fraczek	3fcca40909	eigen sqrt fix and change 1e-5 to epsilon ... test=develop	7 years ago
Qiao Longfei	5fc305220c	Merge pull request #13787 from PaddlePaddle/revert-13637-optimize-opyreader ... Revert "optimize pyreader"	7 years ago
nhzlx	9445502f90	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into trt_dy_lib ... test=develop	7 years ago
chengduo	e1904ac2c8	Add doc (#13765) ... test=develop	7 years ago
nhzlx	d347ea689a	fix comments	7 years ago
chengduo	e1761709f8	Set the right shape of selected_rows (#13723) ... * set the right shape of selected_rows test=develop * enhance check * fix activation_op * remove cast * use ShareDimInfo replace SetDim and ShareLod * use ShareDimAndLod test=develop * follow comment test=develop * check whether the input has lod test=develop * Split ShareDimAndLod test=develop * checkout clip.py test=develop	7 years ago
tensor-tang	3ee8f2c6cf	thread local jit kernels ... test=develop	7 years ago
tensor-tang	9131a35676	replace the lstm compute with jitkernel ... test=develop	7 years ago
Qiao Longfei	9d087d5139	Revert "optimize pyreader" ... test=develop	7 years ago
tensor-tang	b55c247678	add lstm compute unit test	7 years ago
nhzlx	f3af90d121	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into trt_dy_lib ... test=develop	7 years ago
nhzlx	f569095084	add tensorrt api lib to paddle_fluid	7 years ago
qingqing01	6094a72308	Fix bug in reduce_op caused by PR #13534 (#13748) ... * Fix bug in reduce_op caused by PR #13534 * Fix output shape and enhance unit test. test=develop	7 years ago
Tao Luo	59c306eb52	Merge pull request #13776 from luotao1/revert_fast_math ... revert with_fast_math to ON	7 years ago
Tao Luo	84a55155ec	revert with_fast_math to ON ... test=develop	7 years ago
Wu Yi	cc36bab184	fix manylinux multi arch docker build test=develop (#13770)	7 years ago
Qiao Longfei	b1d5135ffb	Merge pull request #13637 from jacquesqiao/optimize-opyreader ... optimize pyreader	7 years ago
dzhwinter	a46e30aa6d	enhance isinf/isnan in tensor util, avoid copy back to cpu (#12688) ... * "avoid copy back to cpu" * "add infinity support" * "fix ci" * "add cpu macro" * rerun ci; test=develop * "fix api" test=develop * test=develop * test=develop * test=develop * test=develop * test=develop	7 years ago
tensor-tang	2a00969165	optimize lstm jitkernel keq8 ... test=develop	7 years ago
tensor-tang	f2adaf1c3e	add vrelu and lstm kernel ... test=develop	7 years ago
Xin Pan	943e4deb23	Merge pull request #13750 from panyx0718/fix ... clean unused code and small optimize	7 years ago
Jacek Czaja	9f15d8817e	- Cleanup as suggessted by reviewers ... test=develop	7 years ago
Wu Yi	25262ed076	fix cuda9 docker build test=develop (#13701) ... * fix cuda9 docker build test=develop * update test=develop * update test	7 years ago
Sylwester Fraczek	78f98294c2	conv bn fuse pass ... review fix review from hshen14 fix test=develop fix error in broadcast and code cleanup rename bias -> eltwise and added macro to shorten code formatting	7 years ago
Jacek Czaja	ae8b4717cc	- Cleaning fused_embedding_fc_lstm op ... test=develop	7 years ago
Jacek Czaja	fd31b54cf1	- Removed disabled code ... test=develop	7 years ago
Jacek Czaja	f9da2d6416	- Removed disabled diagnostic code ... test=develop	7 years ago
Jacek Czaja	809dbc5c17	- Added file for fused_embedded_fc_lstm_op unit test ... - Work in progress on unit test for fused_embedding_fc_lstm op - Added bias caching and ref x computing - Small update unit test - temporary storage - Fix to batchcompute - Cosmetic fixes - Style fixes	7 years ago
Tao Luo	75bd0f188b	Merge pull request #13754 from luotao1/fast_math ... disable EIGEN_FAST_MATH and use_fast_math	7 years ago
qiaolongfei	5238a7f5b9	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into optimize-opyreader ... test=develop	7 years ago
tensor-tang	e6d8aca3bf	refine code and fix	7 years ago
qingqing01	41e4f7ea0a	Optimize Topk when height is large. (#13710)	7 years ago
xuezhong	65ed45a154	Merge pull request #13717 from chengduoZH/enhance_while ... Add nodes for Dyrnn	7 years ago
minqiyang	bcd8c2ccc3	Add unit test	7 years ago
Tao Luo	28889caea5	disable EIGEN_FAST_MATH and use_fast_math ... test=develop	7 years ago
tensor-tang	ea7dc9cbf6	Merge remote-tracking branch 'ups/develop' into fea/jitkernel ... test=develop	7 years ago
Xin Pan	d2079b1ddb	clean unused code and small optimize ... test=develop	7 years ago
tensor-tang	2513b2cc4e	fix bug vtanh	7 years ago
chengduoZH	e59ab42caa	add nodes for drnn ... test=develop	7 years ago
Xin Pan	ab798a2832	clarify the fraction_of_gpu_memory flag ... test=develop	7 years ago
Tao Luo	d770b9bda3	Merge pull request #13663 from luotao1/resnet50_ut ... add resnet50 inference unit-test	7 years ago
dzhwinter	32c260cd1f	"fix operators cmake" (#13581) ... * "fix operators cmake" * "rerun ci" test=develop	7 years ago
Tao Luo	6ef6a9180a	Merge pull request #13727 from Sand3r-/mgallus/enable-mkldnn-naive-exe ... Enable MKL-DNN in Naive Executor and Analysis Predictor	7 years ago
minqiyang	f20fc95539	Resize output ddims and rows	7 years ago
qiaolongfei	91756a5a90	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into optimize-opyreader	7 years ago
Zeng Jinle	8cd17c04c1	Merge pull request #13718 from sneaxiy/fix_eager_deletion ... Fix eager deletion bug in fetch_op_handle	7 years ago
Michal Gallus	09d9d77a8f	Enable MKLDNN in Naive Executor ... test=develop	7 years ago
Jiabin Yang	8e63bc2307	Merge pull request #13700 from JiabinYang/fix/mac_ci_job ... refine paddle_build shell to fix permission denied problem on ci	7 years ago
tensor-tang	5ef14dd386	Merge pull request #13715 from tensor-tang/fix/op ... bugfix fusion lstm and gru batch,seq mode switch	7 years ago
minqiyang	67308822f8	Add selected_rows merge for clip_by_norm op ... test=develop	7 years ago
sneaxiy	9606b37ce4	test=develop	7 years ago
Xin Pan	c0dfd5eee8	Merge pull request #13712 from luotao1/doc_element ... refine elementwise doc	7 years ago
tensor-tang	ea0b98e007	bugfix: fusion lstm and gru batch,seq mode switch ... test=develop	7 years ago
Tao Luo	69ed75e77c	refine elementwise doc ... test=develop	7 years ago
Tao Luo	49cd43000c	Merge pull request #12981 from chenwhql/sequence_erase_op_infershape_note_polish ... Doc: unified infershape format	7 years ago
JiabinYang	248400f43a	test=develop	7 years ago
tensor-tang	cf8c8e72bd	add vtanh and unit test	7 years ago
Tao Luo	067b8582af	Merge pull request #13625 from wanghaoshuang/fix_warning_roi ... Fix warning of roi perspective transform op	7 years ago
tensor-tang	b37fe30417	Merge pull request #13690 from wangguibao/fix_cpu_lstm_compute_cc ... Avoid multiple definitions of lstm_compute_ctht when linking libpaddle_fluid.so	7 years ago
dzhwinter	26771f41ba	"fix compile error" (#13579) ... * "fix compile error" * "fix ci" * rerun ci test=develop * test=develop rerun ci	7 years ago
JiabinYang	4cc3c4c976	test=develop	7 years ago
Yu Yang	186b2b138d	Revert "Merge pull request #13201 from reyoung/revert_callstack" (#13697) ... This reverts commit 21bb9e91fc, reversing changes made to 3fa68dc101. test=develop	7 years ago
Tao Luo	a89afd4c22	Merge pull request #13685 from luotao1/naive_cmake ... update libpaddle_fluid.a/so	7 years ago
tensor-tang	d10a9df7b8	add vaddbias and unit test	7 years ago
tensor-tang	3c8b651187	add vsigmoid avx implementations and unit test	7 years ago
luotao1	9cbf2023ab	rollback paddle_inference_helper.h to helper.h ... test=develop	7 years ago
sneaxiy	6f748a035d	test=develop	7 years ago
tensor-tang	55e44761fb	refine code and init vsigmoid	7 years ago
Xin Pan	2f5a7cc470	Merge pull request #13673 from panyx0718/infer ... hide all left over kwargs	7 years ago
wangguibao	1940bc2d83	Avoid multiple definitions of lstm_compute_ctht when linking libpaddle_fluid.so ... test=develop	7 years ago