Paddle

Commit Graph

Author	SHA1	Message	Date
Michał Gallus	269db0d1d1	[DNNL] Fix accuracy in INT8 FC (#22404 ) * Enable quantize to reorder to nchw as well * Correct FC MKL-DNN input dim requirements to accept 3D * Improve DNNL FC format, error and 3D input handling test=develop * Improve error checking in FC test=develop * Improve PADDLE_ENFORCE messages in fc-related files * Remove data layout attribute from obligatory pass args test=develop * Fix message in fc_mkldnn_pass to be logically correct test=develop	5 years ago
joanna.wozna.intel	3099d9d47c	Restore requantize squash (#22399 )	5 years ago
lidanqing	895f8da7d6	change std::cout to log(INFO), vlog (#22316 )	5 years ago
Wojciech Uss	d3a6647372	improve placement pass tests code coverage (#22197 )	5 years ago
joanna.wozna.intel	5b2e98aa17	Add multiple quantize operators fuse (#22062 )	5 years ago
lidanqing	d3a96632fa	Add fc-dequantize squash in cpu_quantize_squash_pass for ernie model (#21714 ) * fc-dequantize squash test=develop * change according to reviews test=develop * change PADDLE_ENFORCE test=develop * add second test when fc-dequant do not fuse test=develop * change all related PADDLE_ENFORCE test=develop	5 years ago
joanna.wozna.intel	d419b859c0	Add reshape int8 mkldnn op (#21428 ) * Add reshape int8 op test=develop * Change test to CPUPlace test=develop * Correct tests test=develop	5 years ago
Michał Gallus	5d7d548275	INT8 Fully-connected (#17641 ) * Implement Int8 FC * Integrate FC into INT8v2 test=develop * int8 FC: transpose weights before computing scales test=develop * Add support for activation_type string in FC test=develop * Disable MKL-DNN's FC in VGG16 and 19 test=develop * Disable FC quantization when mkldnn FC is disabled test=develop * Solve PADDLE_ENFORCES in FC int8 * Fix Paddle enforces and remove const cast test=develop * Fix style changes test=develop * Fix quantizer_tester test and add fc quantization test=develop * Fix FC test fail on CUDA * Remove unnecessary log from quantize placement pass test=develop * Add Thread ID to FC hash key test=develop * Add comments to MKL-DNN FC Kernel test=develop * Refactor quantizer test=develop * Fix linter issues test=develop * Fix crash in slim googlenet test=develop * Fix PADDLE_ENFORCE messages test=develop	5 years ago
joanna.wozna.intel	77c2083586	Add transpose2 INT8 for mkl-dnn (#19424 ) * Add transpose2 INT8 for mkl-dnn test=develop * Fix test_transpose_int8_mkldnn test=develop * Revert "Merge branch 'develop' into transpose_int8_mkldnn_2" This reverts commit 34011bdba4c859abb945e062ab13124f70508054, reversing changes made to 2ce6473f144da298aba4a43d46918f27d463cf7c. * Revert "Revert "Merge branch 'develop' into transpose_int8_mkldnn_2"" This reverts commit 23754dd78ca47ae56881161172b2aacd349aba90. * Add template to TransposeMKLDNNHandler test=develop * Resolve conflict test=develop * Restore get_size and refactor test=develop	5 years ago
hong	8c4573a3cb	GradMaker for dygraph (#19706 ) * refactor dygraph,test=develop * fix failed unittest,test=develop * polish code,test=develop * check windows ci error,test=develop try to fix windows ci error by np.allclose,test=develop * polish vlog and profiler, test=develop * try to fix preceding ops order,test=develop * test transformer in windows ci, test=develop * use python c-api to speed up tracer.trace,test=develop * test=develop, fix docker with paddle nccl problem * test=develop, add ut for debug string and gradient_accumulator * test=develop, add tests for layer/gradient_accumulator/prepared_op * test=develop, fix complie error for test_prepared_op * test=develop, add more ut for dygraph * test=develop, create API.spec for dygraph api change * optimize grad maker; test=develop * optimize grad maker * test * grad make optim; test=develop * fix unittest bugs; test=develop * add dygraph grad op maker and split_op * grad op maker refactor; test=develop * add dygraph grad maker; test=develop * fix op deformable_conv_v1_op bug; test=develop * fix deformable_conv prroi pool bugs; * fix new op grad op maker bug; test=develop * fix split by ref bug; test=develop * fix dygraph auto prune bug; test=develop * fix test_trace bug; test=develop * fix fused emb seq pool bug; test=develop * remove useless code in op_desc file; test=develop * remove useless code, StrVarBaseNode; test=develop * fix review issues; test=develop * fix rank_loss grad maker; test=develop * remove flag in VarBase; test=develop * fix distributed_notify_op compile bug ; test=develop * fix reshape op double grad; test=develop * fix expand as op; test=develop * add impertive type_defs.h for demo_train; test=develop * fix inference lib cmake; test=develop * fix inference lib; test=develop * fix infernce_lib; test=develop * fix inference cmake; test=develop * fix inference lib; test=develop * fix inference lib; test=develop * remove condition dygraph grad maker, modify local name; test=develop * fix split grad maker bug; test=develop * fix pyramid_op bug; test=develop * change travis time out limit; test=develop * restore travis; test=develop * change timeout limit; test=develop	5 years ago
bingyanghuang	9de6772510	Follow comment of Merged QAT PR 18970 (#19979 ) * Follow Wangzhen's comment in PR 18970, test=develop * Review comments, test=develop * Leave fake quantization around mul test=develop * Replace Fake with Real Quantized Mul test=develop * Fix bug in quantize placement pass Nodes in the graph now have checked type instead of node name when they are to be marked for quantization test=develop	6 years ago
joanna.wozna.intel	f5221ac19f	Disable conv requant squash (#20041 ) * Fix conv2d+dequantize squash for residual fusion test=develop * Disable conv-requant squash test=develop	6 years ago
joanna.wozna.intel	3f1d0234ae	Fix conv2d+dequantize squash for residual fusion (#19545 ) * Fix conv2d+dequantize squash for residual fusion test=develop * Change condition test=develop	6 years ago
Yiqun Liu	c5548178b0	A a pass to enable the use of cudnn (#19346 ) * Add a interface to enable cudnn for inference. * Add cudnn_placement_pass. test=develop * Set the default value of cudnn_enabled_op_types to null. test=develop * Write the common basic class, placement_pass_base, to refine the codes. test=develop * Call EnableCUDNN in unittest. test=develop * Refine cudnn_placement_pass tester. * Enable the testing of cudnn_placement_pass in inference's unittest. test=develop * Add the check of op kernels. test=develop	6 years ago
joanna.wozna.intel	2e3ec66be0	Add conv dequant squash for int8 (#18905 )	6 years ago
Adam	97d1db1874	Add generalized Conv+Activation MKLDNN fuse pass creation Part2 (#19237 ) * Add generalized Conv+Activation MKLDNN fuse pass creation Part2 test=develop * Undefined behaviour of GetAttrIfExists<> FIX test=develop	6 years ago
Adam	b837689e97	Add generalized Conv+Activation MKLDNN fuse pass creation (#19072 ) test=develop	6 years ago
joanna.wozna.intel	492a00f53e	Add conv reqantize squash (#18754 ) * Add requantize squash test=develop * Add more precise tests test=develop * REname and REfactor tester test=develop	6 years ago
joanna.wozna.intel	bce72c7fea	Replace Relu with bounded Relu in MobileNetV2 quantization (#18988 ) test=develop	6 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	6 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	6 years ago
Zeng Jinle	3ece61f71e	Remove attribute in Allocator::Allocate (#17878 ) * remove attribute in Allocator::Allocate, test=develop * fix travis ci error, test=develop	6 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	6 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	6 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	6 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	6 years ago
Sylwester Fraczek	bccb0ba49a	fix quantize_squash_pass segfault when no tensor linked to Bias (#17292 ) * fix quantize_squash_pass segfault when there is no tensor linked do Bias input test=develop * add googlenet test test=develop * fix concat CreateKey not using input format test=develop	6 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	6 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	6 years ago
chengduo	ed61d67c73	Fix the interface of Pass::Apply (#16484 ) * modify the interface of Pass::Allay test=develop * Polish code test=develop * Fix Travis CI test=develop * fix Pass::Apply interface test=develop * Fix Travis CI test=develop	6 years ago
Wojciech Uss	46677fb080	Move cpu_quantize_* passes into mkldnn subfolder test=develop	6 years ago
Wojciech Uss	cbe2dbf0db	Add enabling quantization (#16326 ) * Add enabling quantization test=develop * remove unused (here) function	6 years ago
Krzysztof Binias	72253391b6	Add MKL-DNN placement pass tester test=develop	6 years ago
Michal Gallus	6a2bc9a275	Add Conv Residual Connection UT for Projection test=develop	6 years ago
Michał Gallus	c4faf36e7a	MKL-DNN: Add test for conv bias fuse pass (#15824 ) * MKL-DNN: Add test for conv bias fuse pass test=develop * Remove const cast from Conv Bias Pass Test * Add conv with bias test case for conv+bias fuse ut test=develop	6 years ago
Sylwester Fraczek	0b926114c0	add override to ApplyImpl and #pragma once in edited headers add #include<string> in edited headers test=develop	6 years ago
Krzysztof Binias	b1bdcd4de8	Make separate folders for mkldnn codes test=develop	6 years ago

37 Commits (269db0d1d16c0079a0f7039a5717b27e2c139af6)