Paddle

Commit Graph

Author	SHA1	Message	Date
liuwei1031	0d99690809	fix several security bugs reported by security team (#18831 ) * fix security issue, test=develop * bug fix, test=develop * throw an exception when null pointer data with non-zero length PaddleBuf is passed, test=develop	7 years ago
Zhaolong Xing	61238d31f7	Trt fp16 support (#18860 ) * Fix Mask rcnn predictor 1. refine memory optim algorithm to support the model with the block op. 2. output diff : modify the affine channel fuse 3. add condition_block_infer op add interface for setting trt calib table dir test=develop * add the missing files. test=develop * 1 add trt fp16 support test=develop	7 years ago
Zhaolong Xing	26ae6d49e4	Update trt5 for paddle-trt (#18645 ) * update paddle-trt for: 1. fix bug: when batch > 2, core in split plugin. 2. add leaky_relu trt5.0 support (yolov3 from 65ms to 42ms.) 3. add new attr to dropout. 4. shuffle channel, swish, relu6 support test=develop * 1. fix ci test=develop	7 years ago
石晓伟	25d8079140	Fix Bitmain Predictor::Clone() (#18599 ) * update anakin-engine interfaces for content-dnn test=develop * support only-gpu mode of Anakin modify eltwise parse test=develop * modification for thread-safe test=develop * Integrated template instance test=develop * increase template parameters test=develop * support MLU predictor test=develop * update anakin cmake files test=develop * update TargetWrapper::set_device * update the initialization of anakin subgraph test=develop * use the default constructor of base class test=develop * load model from buffer with length test=develop * modify the access level of class test=develop * support anakin for bitmain arch test=develop * remove files * checkout cmakelists test=develop * modify interfaces test=develop * add cmake dependments test=develop * enforce the outputs of net test=develop	7 years ago
Tao Luo	076f833110	add config.SetMkldnnCacheCapacity api for mkldnn cache clear strategy (#18580 ) * add config.SetMkldnnCacheCapacity api for mkldnn cache clear strategy test=develop * enhance MkldnnPostReset test=develop * add comments for mkldnn_cache_capacity field test=develop	7 years ago
Jiabin Yang	667f88f9a6	Fix/gcc 4.8 ubt link error (#18558 ) * test=develop, fix docker with paddle nccl problem * test=develop, fix/gcc_4.8_ubt_link_error * test=develop, fix code format	7 years ago
Zhaolong Xing	88b52a27fe	Inference: fix mask rcnn model diff, optim memory usage, memory leak. (#18532 ) * Fix Mask rcnn predictor 1. refine memory optim algorithm to support the model with the block op. 2. output diff : modify the affine channel fuse 3. add condition_block_infer op add interface for setting trt calib table dir test=develop * add the missing files. test=develop	7 years ago
石晓伟	1529154821	Support Bitmain Anakin (#18542 ) * update anakin-engine interfaces for content-dnn test=develop * support only-gpu mode of Anakin modify eltwise parse test=develop * modification for thread-safe test=develop * Integrated template instance test=develop * increase template parameters test=develop * support MLU predictor test=develop * update anakin cmake files test=develop * update TargetWrapper::set_device * update the initialization of anakin subgraph test=develop * use the default constructor of base class test=develop * load model from buffer with length test=develop * modify the access level of class test=develop * support anakin for bitmain arch test=develop * remove files * checkout cmakelists test=develop	7 years ago
石晓伟	047bba855b	Remove the obsolete cmake options (#18481 ) * remove the obsolete cmake options, test=develop * remove unittests, test=develop	7 years ago
Tao Luo	3123d18787	remove unused AnalysisPredictor::SetMkldnnThreadID() (#18444 ) test=develop	7 years ago
Michał Gallus	7023a86c3a	Fix Pooling output scale (#18186 ) * Int8: Fix Pooling output scale test=develop * Update scales quantization for certain operators These include: concat, transpose, pool and reshape. test=develop * Move concat minimum scale finding to quantizer test=develop	7 years ago
Michał Gallus	8409693272	Reset DeviceContext after quantization warmup (#18182 ) test=develop	7 years ago
Sylwester Fraczek	9252e8fa08	add int8 mkldnn prior_box (#17242 ) add prior_box quantization code add scale algo rules for prior box test=develop	7 years ago
wopeizl	daa32d5383	fix package generation for inference test=develop (#18220 )	7 years ago
翟飞跃	802ea50956	fix spelling errors (#17941 ) * fix spelling errors; test=develop * Update API.spec update md5 * Update API.spec * change the order of api;test=develop	7 years ago
石晓伟	04ea7cb069	modify the access level of anakin engine (#18015 ) test=develop	7 years ago
石晓伟	bce259e5bf	Update the Anakin interfaces for content-dnn and MLU (#17890 ) * update anakin-engine interfaces for content-dnn test=develop * support only-gpu mode of Anakin modify eltwise parse test=develop * modification for thread-safe test=develop * Integrated template instance test=develop * increase template parameters test=develop * support MLU predictor test=develop * update anakin cmake files test=develop * update TargetWrapper::set_device * update the initialization of anakin subgraph test=develop * use the default constructor of base class test=develop	7 years ago
石晓伟	d008260fa8	update the initialization of anakin subgraph (#17880 ) test=develop	7 years ago
Zhaolong Xing	ae576f3c68	fix: when use the load model from memory mode, the RAM occupy is high (#17788 ) test=develop	7 years ago
翟飞跃	993c703bcc	INT8 MKL-DNN v2 integrate to slim (#17634 ) * refactor PR 16865 * delete mergetool files * test=develop * test=develop * test=develop * test=develop * create dir for int8 model before call SaveOptimModel * test=develop * mkldnn int8 only support linux; test=develop * refine code; test=develop * remove comment; test=develop * refine code; test=develop * fix bug; test=develop * add exception for mkldnn_post_training_strategy * reuse int8v2 CAPI dataset; test=develop * fix accuracy check bug; test=develop * remove tab * convert files to unix format * test=develop * reduce CI time;test=develop * reduce CI time and refine code;test=develop * refine comment; test=develop * add cmake FLAGS;test=develop * remove predict_num;test=develop	7 years ago
Tao Luo	e089e454a1	make omp thread num default 1 after inference run (#17801 ) test=develop	7 years ago
mozga-intel	5eb81fe595	Capi for a ngraph engine (#17037 )	7 years ago
lidanqing	04b6c29ee0	Improve mobilenetv2 INT8 performance by using INT8 relu as post-op (#17570 ) * add INT8 conv+relu6 fuse and enbale mobilentv2 INT8 test test=develop * change fasle and 0.0 to fuse_brelu and brelu_threshold test=develop change the "fuse_relu\|\|fuse_brelu" to "unsigned_output" test=develop * Use relu instead of brelu as INT8 post-op because INT8 brelu is not enabled in mkldnn v0.18 test=develop * continuous-integration fix test=develop	7 years ago
Jacek Czaja	6d8075ecef	[MKL-DNN] conv_transpose mkldnn bias pass (#17644 ) * - changes to graph detector - Changes to pass - Added ut for new pass - use_pass - Added pass to mkldnn passes - fix to registration - improved verbose messaging for conv bias passes - Lint fixes test=develop * - Lint fixes test=develop	7 years ago
Sylwester Fraczek	96845d2168	add Concat quantization (#17448 ) * add Concat quantization add unit test for quantizing concat fix for wrong value when the input is not in map of calculated scales add use_quantizer to concat_op.cc add scale_algo rules for concat test=develop * missing fix for multiple inputs quantize-squash * wojtuss review fix: adding comment test=develop	7 years ago
Zhen Wang	8bd651b7ed	Fix the bug in the AnalysisPredictor and add more directions about io APIs. (#17639 ) * fix the bug that sub_scope_ may be null in AnalysisPredictor::Run. * add more directions about io APIs' docs. * update the API.spec. test=develop test=document_preview	7 years ago
Zeng Jinle	4aa931dd85	Code clean of Allocator (#17602 ) * Revert "Revert "Fix allocator bug"" This reverts commit `174d0d0b90`. * Revert "fix travis ci" This reverts commit `5656fa9f7c`. test=develop * add inlined_vector.h, test=develop * add inlined_vector_test,test=develop * clean code of allocator,test=develop * delete zero_size_allocator.h,test=develop * fix failed unittest,test=develop	7 years ago
Zhaolong Xing	61221ebc28	TRT: Support set dynamic range in int8 mode. (#17524 ) * fluid int8 train and trt int8 predict align. trt int8 predict init op converter * 2. align fluid int8 train and trt int8 inference. enhance quant dequant fuse pass enhance op converter, trt engine, trt engine op, trt subgraph pass. * 3. add delete_quant_dequant_pass for trt test=develop * 4. add the missing file test=develop * 5. i modify the c++ interface, but forget to modify the pybind code fix the IS_TRT_VERSION_GE bug, and fix elementwise op converter test=develop	7 years ago
Michał Gallus	0c39b97b4e	[MKL-DNN] Add Fully Connected Op for inference only(#15226 ) * fuse mul and elementwise add to fc * Reimplement the FC forward operator * Fix FC MKLDNN integration by transposing weights * Add FC MKLDNN Pass test=develop * FC MKLDNN Pass: change memcpy to std::copy * Fix MKLDNN FC handling of mismatch input and weights dims * Lower tolerance for MKL-DNN in resnet50 test test=develop * Adjust FC to support MKLDNN Op placement test=develop * Adjust Placement Op to set use_mkldnn attribute for graph test=develop * MKLDNN FC: fix weights format so that gemm version is called test=develop * FC MKLDNN: Remove tolerance decrease from tester_helper * FC MKL-DNN: Refactor the code, change input reorder to weight reorder * MKL-DNN FC: Introduce operator caching test=develop * FC MKL-DNN: Fix the tensor type in ExpectedKernelType test=develop * FC MKL-DNN: fix style changes test=develop * FC MKL-DNN: fallback to native on non-supported dim sizes test=develop * FC MKLDNN: fix CMake paths test=develop * FC MKLDNN: Refine placement pass graph mkldnn attribute test=develop * Fix Transpiler error for fuse_conv_eltwise test=develop * Fix missing STL includes in files test=develop * FC MKL-DNN: Enable new output size computation Also, refine pass to comply with newest interface. test=develop * FC MKL-DNN: enable only when fc_mkldnn_pass is enabled * FC MKL-DNN: Allow Weights to use oi or io format * FC MKL-DNN: Adjust UT to work with correct dims test=develop * Enable MKL DEBUG for resnet50 analyzer test=develop * FC MKL-DNN: Improve Hashing function test=develop * FC MKL-DNN: Fix shape for fc weights in transpiler * FC MKL-DNN: Update input pointer in re-used fc primitive * Add log for not handling fc fuse for unsupported dims test=develop * FC MKL-DNN: Move transpose from pass to Op Kernel test=develop * FC MKL-DNN: Disable transpose in unit test test=develop * FC MKL-DNN: Remove fc_mkldnn_pass from default list * Correct Flag for fake data analyzer tests test=develop * FC MKL-DNN: Add comment about fc mkldnn pass disablement test=develop * FC MKL-DNN: Disable fc in int8 tests test=develop	7 years ago
Sylwester Fraczek	5b2a3c4b12	Conv concat relu quantization (#17466 ) * add conv_concat_relu fuse test=develop * add test code test=develop * added missing include with unordered_map test=develop * review fixes for wojtuss test=develop * remove 'should (not) be fused' comment statements one of them was invalid anyway test=develop	7 years ago
guomingz	2281ebf0f3	Enable the convolution/relu6(bounded_relu) fusion for FP32 on Intel platform. (#17130 ) * Relu6 is the bottleneck op for Mobilenet-v2. As the mkldnn supports the conv/relu6 fusion, we implement it fusion via cpass way. Due to the int8 enabling for this fusion will be supported in MKLDNN v0.20, so this PR is focused on the fp32 optimization. Below table shows the benchmark(FPS) which measured on skx-8180(28 cores) Batch size \| with fusion \| without fusion -- \| -- \| -- 1 \| 214.7 \| 53.4 50 \| 1219.727 \| 137.280 test=develop * Fix the format issue test=develop * Add the missing nolint comments. test=develop * Fix the typos. test=develop * Register the conv_brelu_mkldnn_fuse_pass for the MKLDNN engine. test=develop * Adjust the indentation. test=develop * Add the test_conv_brelu_mkldnn_fuse_pass case. test=develop * Slightly update the code per Baidu comments. Let the parameter definition embedded into the code. That's will make the code easy to understand. test=develop	7 years ago
liuwei1031	ba70cc499e	fix security bugs : (#17464 ) http://newicafe.baidu.com:80/issue/PaddleSec-33/show?from=page http://newicafe.baidu.com:80/issue/PaddleSec-28/show?from=page http://newicafe.baidu.com:80/issue/PaddleSec-25/show?from=page http://newicafe.baidu.com:80/issue/PaddleSec-24/show?from=page http://newicafe.baidu.com:80/issue/PaddleSec-21/show?from=page http://newicafe.baidu.com:80/issue/PaddleSec-20/show?from=page test=develop	7 years ago
Tao Luo	32da5e9c3d	remove unused expected_kernel_cache_pass (#17486 ) test=develop	7 years ago
wopeizl	ca3ba378c7	fix the random compilation failure on windows test=develop (#17475 ) * fix the random compilation failure on windows	7 years ago
Zhen Wang	4a1b7fec96	Add setting Scope function for the graph class (#17417 ) * add set_not_owned function for graph * add scope set. test=develop * add scope_ptr enforce not null before setting.test=develop	7 years ago
Zhaolong Xing	7a3bb061d8	fix: (#17279 ) 1. infernce multi card occupy 2. facebox model inference occupy too much test=develop	7 years ago
Wojciech Uss	984aa90583	improved unit test output (#17266 ) added printing data type to differentiate int8 and fp32 latency results test=develop	7 years ago
石晓伟	a72dbe9abf	Cherry-pick benchmark related changes from release/1.4 (#17156 ) * cherry-pick commit from `8877054` * cherry-pick commit from `3f0b97d` * cherry-pick from 16691:Anakin subgraph support yolo_v3 and faster-rcnn (cherry picked from commit `8643dbc233`) * Cherry-Pick from 16662 : Anakin subgraph cpu support (cherry picked from commit `7ad182e16c`) * Cherry-pick from 1662, 16797.. : add anakin int8 support (cherry picked from commit `e14ab180fe`) * Cherry-pick from 16813 : change singleton to graph RegistBlock test=release/1.4 (cherry picked from commit `4b9fa42307`) * Cherry Pick : 16837 Support ShuffleNet and MobileNet-v2 Support ShuffleNet and MobileNet-v2, test=release/1.4 (cherry picked from commit `a6fb066f90`) * Cherry-pick : anakin subgraph add opt config layout argument #16846 test=release/1.4 (cherry picked from commit `8121b3eccb`) * 1. add shuffle_channel_detect (cherry picked from commit `6efdea8997`) * update shuffle_channel op convert, test=release/1.4 (cherry picked from commit `e4726a066f`) * Modify symbol export rules test=develop	7 years ago
Leo Zhao	54636a1982	call SetNumThreads everytime to avoid missing omp thread setting (#17224 ) * call SetNumThreads everytime to avoid missing omp thread setting resolve #17153 test=develop * add paddle_num_threads into config for test_analyzer_pyramid_dnn resolve #17153 test=develop	7 years ago
wopeizl	83c4f7721f	use two GPUs to run the exclusive test test=develop (#17187 )	7 years ago
luotao1	490e746269	fix runtime_context_cache bug when gpu model has an op runs only on cpu test=develop	7 years ago
wopeizl	d9991dccdd	add parallel build script to ci … (#16901 ) * add parallel build script to ci test=develop * 1. classify the test case as single card/two cards/multiple cards type 2. run test case according to the run type	7 years ago
Tao Luo	aa7b975bf6	disable runtime_context_cache pass by default test=develop	7 years ago
Tao Luo	ca8b8fa0bd	Merge pull request #16830 from Superjomn/fix/tmp-memory-optim fix memory optim temporarily	7 years ago
lijianshe02	de26df440b	add SaveOptimModel interface in analysis_predictor.h and test it in a… (#16441 ) * add SaveOptimModel interface in analysis_predictor.h and test it in analyzer_dam_tester and analyzer_resnet50_tester test=develop	7 years ago
superjomn	f58c3ec189	fix memory optim temporarily test=develop	7 years ago
liuwei1031	85363848a1	Security issue (#16774 ) * disable memory_optimize and inpalce strategy by default, test=develop * fix security issue http://newicafe.baidu.com:80/issue/PaddleSec-3/show?from=page http://newicafe.baidu.com:80/issue/PaddleSec-8/show?from=page http://newicafe.baidu.com:80/issue/PaddleSec-12/show?from=page http://newicafe.baidu.com:80/issue/PaddleSec-32/show?from=page http://newicafe.baidu.com:80/issue/PaddleSec-35/show?from=page http://newicafe.baidu.com:80/issue/PaddleSec-37/show?from=page http://newicafe.baidu.com:80/issue/PaddleSec-40/show?from=page http://newicafe.baidu.com:80/issue/PaddleSec-43/show?from=page http://newicafe.baidu.com:80/issue/PaddleSec-44/show?from=page http://newicafe.baidu.com:80/issue/PaddleSec-45/show?from=page test=develop * revert piece.cc, test=develop * adjust api.cc,test=develop	7 years ago
tensor-tang	d6c1b5a73b	disable seqpool concat pass by default saving CI time test=develop	7 years ago
luotao1	226596a296	Merge branch 'develop' into core_opt_choose_kernel	7 years ago
luotao1	bd636a9ea6	test_analyzer_int8 tests use default pass order test=develop	7 years ago

1 2 3 4 5 ...

427 Commits (22fa4c2d2440208870eb94de8694c05f2605cfe8)