Commit Graph

3782 Commits (13816dd4acdabd21a715b3b1c63fb43cdbac7622)

Author SHA1 Message Date
dengkaipeng ad897304f9 fix pre-commit. test=develop
6 years ago
dengkaipeng 72a18bb160 add bbox range limit. 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
6 years ago
Tao Luo ccc7c358b3
Merge pull request #16104 from tensor-tang/refine/jit
6 years ago
Zeng Jinle 472f16b5aa
Merge pull request #16063 from sneaxiy/enhance_gc
6 years ago
luotao1 31ccaf0916 add all_kernels_must_compute_runtime_shape example for speedup infershape
6 years ago
tensor-tang 14d871121b enhance jitkernel unit test
6 years ago
chengduo ad80bde824
Revert "Revert "Add Event for TensorCopy"" (#16035)
6 years ago
tensor-tang cfc83c1445 refine jitcodekey and enhance unit tests
6 years ago
tensor-tang 6ff230a624 Merge remote-tracking branch 'ups/develop' into refine/jit
6 years ago
sneaxiy cfd012e2cb add unittest
6 years ago
sneaxiy d7407c90aa refine cross_entropy mem
6 years ago
sneaxiy 732fa00eaf disable gc in recurrent_op currently
6 years ago
tink2123 e4e0d03459 fix format
6 years ago
Tink_Y 5579fae1d2
Update activation_op.cc
6 years ago
tensor-tang 45bdd84dac enhance the jitkernel helper and add unit tests
6 years ago
tink2123 837ad7f86f Add the inverse trigonometric function
6 years ago
tensor-tang 14a764c930 simplify the jitkernel templates and tests
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)
6 years ago
Zhaolong Xing 3d63aa0a11
Merge pull request #15729 from NHZlX/add_static_model_load_for_trt
6 years ago
jerrywgz b0e3c02410
Merge pull request #15952 from jerrywgz/fpn_ops
6 years ago
tensor-tang 802f362ac4 unify the kernelfuncs cache and add unit test
6 years ago
Yiqun Liu 36e2d3241e
Enhance the op benchmark: (#16066)
6 years ago
tensor-tang 9be825a982
polish the cast op doc (#16078)
6 years ago
jerrywgz 847bb6a279 Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fpn_ops
6 years ago
jerrywgz 893789a0d1
Merge pull request #16050 from jerrywgz/add_box_decoder_and_assign
6 years ago
xiaolil1 a177d48217 Add Requantize OP (#15318)
6 years ago
chengduo f5a3751845
Refine recurrent_op (#16027)
6 years ago
sneaxiy 7b608396fe fix travis-ci format check
6 years ago
tensor-tang 6057f36208
Merge pull request #15996 from tensor-tang/op/embgrad
6 years ago
chengduo c67afb0f76
Fix reshape bug (#16069)
6 years ago
sneaxiy 33138a421d remove match check
6 years ago
Zhen Wang 8063b31e2d Reduce redundant code for channel wise dequant op. test=develop
6 years ago
Zhen Wang e8f9dac7ab Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into channel_wise_quant_op
6 years ago
Zhen Wang 806832e091 update the input format of channel wise dequantize op.
6 years ago
jerrywgz 072eca348a refine doc, test=develop
6 years ago
Kaipeng Deng 6d8771b55c
Merge pull request #15864 from heavengate/spectral_norm
6 years ago
sneaxiy 814a759061 merge develop
6 years ago
sneaxiy 597dc65e76 enhance gc
6 years ago
baojun da45fbdaf5 fix tanh typo test=develop (#16049)
6 years ago
whs 0f99d24083
Make sequence_erase op support for input with multi-level LoD. (#15982)
6 years ago
Zhen Wang 89dee160d1 add channel wise dequantize op.
6 years ago
jerrywgz b4f5180299 fix doc, test=develop
6 years ago
jerrywgz a1ef7df865 refine code, test=develop
6 years ago
tensor-tang 12eb9aecde Merge remote-tracking branch 'ups/develop' into op/embgrad
6 years ago
jerrywgz d497bd9079 resolve conflict, test=develop
6 years ago
jerrywgz 41471d28ac add box_coder_and_assign, test=develop
6 years ago
lidanqing 02c106c717 MKLDNN: Add UT for conv_transpose_mkldnn op. (#16030)
6 years ago
dengkaipeng 3eab9e4b95 fix statement. test=develop
6 years ago
dengkaipeng e37f5ab5b1 fix API.spec. test=develop
6 years ago
dengkaipeng 54bbbfa71f fix doc statement. test=develop
6 years ago
dengkaipeng c1a69e3ea0 refine doc. test=develop
6 years ago
dengkaipeng 65d375a09f fix format. test=develop
6 years ago
dengkaipeng 82d514345c fix spectral_norm doc. test=develop
6 years ago
dengkaipeng 2ea5843cbf add doc and test_layers. test=develop
6 years ago
dengkaipeng 037855f42d fix attr dim calc. test=develop
6 years ago
dengkaipeng 70dbd59839 add grad kernel for spectral_norm. test=develop
6 years ago
dengkaipeng 72509ec3bd add unittest for spectral_norm. test=develop
6 years ago
dengkaipeng 3bf1ae9b59 add spectral_norm forwarn kenel
6 years ago
Zhen Wang 545247d7b4 add channel wise quantize op.
6 years ago
tensor-tang b16dabd7e0 refine vbroadcast jitcode
6 years ago
tensor-tang c2e56e6bbc Merge remote-tracking branch 'ups/develop' into op/embgrad
6 years ago
chengduo e2da3a5b22
Revert "Add Event for TensorCopy" (#16022)
6 years ago
baojun 9aaea38c0a fix cpplint test=develop (#16028)
6 years ago
chengduo 7235fd662b
Add Event for TensorCopy (#15953)
6 years ago
Tink_Y 31d830de9f refine image_resize annotation (#15976)
6 years ago
tensor-tang 641b3cccce add vbroadcast mkl code and jitcode
6 years ago
tensor-tang 41a1270856 add vbroadcast jitkernel refer code and use it
6 years ago
tensor-tang 867e93b21a add jitkernel vcopy and speedup unit test time
6 years ago
jerrywgz c31da7899a refine code, test=develop
6 years ago
Yiqun Liu 798925453e
Revert "Optimize while_op when is_test is true. (#15811)" (#15968)
6 years ago
Yiqun Liu 87248281f7
Fix error in CUDA kernel of beam_search. (#15957)
6 years ago
jerrywgz e8a8fe07e7 fix code for windows CI, test=develop
6 years ago
jerrywgz 149411762a add gpu kernel, test=develop
6 years ago
Tao Luo 4efdebc6f6
Merge pull request #15931 from yihuaxu/develop_2c5c7b2a7_gelu_mkl_opt
6 years ago
tensor-tang e5f9d3a47c
Merge pull request #15892 from tensor-tang/jit/sgd
6 years ago
Tao Luo e6bab55f1b
Merge pull request #15959 from luotao1/infershape_refine
6 years ago
Yiqun Liu 613d9d0756
Optimize while_op when is_test is true. (#15811)
6 years ago
xiaolil1 1abddd8d97 Optimize Quantize Op with primitive reuse. (#15929)
6 years ago
Tao Luo 7ec97a0a7e
Merge pull request #15930 from xiaolil1/dequantize-reuse
6 years ago
nhzlx 2eff3e26b6 Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into add_static_model_load_for_trt
6 years ago
nhzlx 06a088a199 fix comments and fix cpplint
6 years ago
luotao1 34404f9c31 refine infershape of sequence_enumerate, hash and fuse_emb_seq_pool
6 years ago
baojun f285191fb3 Added adam op test=develop (#15710)
6 years ago
jerrywgz b92ef45fe9
Merge pull request #15678 from jerrywgz/refine_softmax_with_cross_entropy
6 years ago
mozga-intel 558f94cd77 Register sum operator (#15889)
6 years ago
tensor-tang 58b8231338
added concat op test=develop (#15946)
6 years ago
Tao Luo 47d36b2008
Merge pull request #15924 from baojun-nervana/ngraph_v14
6 years ago
jerrywgz 0f652f304c add distribute fpn proposals op, test=develop
6 years ago
dzhwinter 225c11a91f polish cudnn related code and fix bug. (#15164)
6 years ago
Yiqun Liu 454f4f2140
Rewrite is_empty op to avoid unnecessary data transform. (#15509)
6 years ago
xiaolil1 6724be2b0d INT8 Pool kernel Key Creation Optimization. (#15883)
6 years ago
xiaoli.liu@intel.com c4187dbd7c Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into dequantize-reuse
6 years ago