1. 24 5月, 2019 3 次提交
    • M
      [MKL-DNN] Add Fully Connected Op for inference only(#15226) · 0c39b97b
      Michał Gallus 提交于
      * 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
      0c39b97b
    • S
      Conv concat relu quantization (#17466) · 5b2a3c4b
      Sylwester Fraczek 提交于
      * 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
      5b2a3c4b
    • S
      fix quantize_squash_pass segfault when no tensor linked to Bias (#17292) · bccb0ba4
      Sylwester Fraczek 提交于
      * 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
      bccb0ba4
  2. 23 5月, 2019 1 次提交
  3. 22 5月, 2019 1 次提交
    • G
      Enable the convolution/relu6(bounded_relu) fusion for FP32 on Intel platform. (#17130) · 2281ebf0
      guomingz 提交于
      * 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
      2281ebf0
  4. 20 5月, 2019 2 次提交
  5. 16 5月, 2019 2 次提交
  6. 08 5月, 2019 1 次提交
  7. 07 5月, 2019 2 次提交
    • Z
      Enhance inplace/mem-opt pass and enhance softmax_with_cross_entropy op inplace (#17225) · 4f859408
      Zeng Jinle 提交于
      * add use_cuda to inplace pass,test=develop
      
      * add test softmax_with_xe_inplace test,test=develop
      
      * fix potential inplace bug
      test=develop
      
      * add more skip vars in mem opt pass,test=develop
      
      * follow comment,test=develop
      
      * follow comments,move duplicate out arg check to program->graph,test=develop
      4f859408
    • Cherry-pick benchmark related changes from release/1.4 (#17156) · a72dbe9a
      石晓伟 提交于
      * cherry-pick commit from 88770542
      
      * cherry-pick commit from 3f0b97df
      
      * cherry-pick from 16691:Anakin subgraph support yolo_v3 and faster-rcnn
      
      (cherry picked from commit 8643dbc2)
      
      * Cherry-Pick from 16662 : Anakin subgraph cpu support
      
      (cherry picked from commit 7ad182e1)
      
      * Cherry-pick from 1662, 16797.. : add anakin int8 support
      
      (cherry picked from commit e14ab180)
      
      * Cherry-pick from 16813 : change singleton to graph RegistBlock
      test=release/1.4
      
      (cherry picked from commit 4b9fa423)
      
      * Cherry Pick : 16837 Support ShuffleNet and MobileNet-v2
      
      Support ShuffleNet and MobileNet-v2, test=release/1.4
      
      (cherry picked from commit a6fb066f)
      
      * Cherry-pick : anakin subgraph add opt config layout argument #16846
      test=release/1.4
      
      (cherry picked from commit 8121b3ec)
      
      * 1. add shuffle_channel_detect
      
      (cherry picked from commit 6efdea89)
      
      * update shuffle_channel op convert, test=release/1.4
      
      (cherry picked from commit e4726a06)
      
      * Modify symbol export rules
      
      test=develop
      a72dbe9a
  8. 30 4月, 2019 2 次提交
    • T
      fix bn fuse vardesc and add model saver (#17143) · 79ed1c76
      tensor-tang 提交于
      * fix bn fuse vardesc and add model saver
      
      test=develop
      
      * unify save model in test helper
      
      test=develop
      
      * fix mkdir on windows
      
      test=develop
      
      * remove magic number use bn bias var desc
      
      test=develop
      79ed1c76
    • Z
      Rewrite inplace pass and fix gc bug (#17126) · 4e1bc6e8
      Zeng Jinle 提交于
      * fix op graph view
      test=develop
      
      * rewrite inplace pass and fix reference count pass bug
      test=develop
      
      * fix unittest failed
      test=develop
      
      * follow comments, test=develop
      4e1bc6e8
  9. 12 4月, 2019 1 次提交
  10. 11 4月, 2019 1 次提交
  11. 08 4月, 2019 1 次提交
  12. 04 4月, 2019 1 次提交
  13. 02 4月, 2019 1 次提交
  14. 28 3月, 2019 2 次提交
    • N
      Anakin ssd support · d065b5bf
      nhzlx 提交于
      refine trt first run
      add quant dequant fuse pass
      omit simplify_anakin_priorbox_detection template
      omit transpose_flatten_concat_fuse template
      test=develop
      d065b5bf
    • C
      Fix the interface of Pass::Apply (#16484) · ed61d67c
      chengduo 提交于
      * 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
      ed61d67c
  15. 27 3月, 2019 1 次提交
  16. 25 3月, 2019 1 次提交
  17. 21 3月, 2019 2 次提交
  18. 20 3月, 2019 5 次提交
  19. 19 3月, 2019 4 次提交
  20. 18 3月, 2019 4 次提交
    • M
      Polish code style · b40e41fb
      minqiyang 提交于
      test=develop
      b40e41fb
    • M
      Take DataType and VarType apart · 36dce65b
      minqiyang 提交于
      test=develop
      36dce65b
    • L
      refine with comments · cc0ae1f1
      luotao1 提交于
      test=develop
      cc0ae1f1
    • W
      Add cpu_quantize_pass for C-API quantization (#16127) · 2579ade4
      Wojciech Uss 提交于
      * Add cpu_quantize_pass for C-API quantization
      
      test=develop
      
      * add cpu_quantize_pass test
      
      * fix lint: add include memory unorderd_map and unordered_set
      
      test=develop
      
      * fuse_relu 1
      
      test=develop
      
      * tuned 2 without squash
      
      * fixes
      
      test=develop
      
      * remove unused vars
      
      test=develop
      
      * refactored
      
      test=develop
      
      * fix lint c-style cast -> C++ style cast
      
      test=develop
      
      * remove QuantMax and c style casts
      
      test=develop
      
      * last usage of QuantMax removed
      
      test=develop
      
      * Fix Analysis Predictor UT
      
      Check if memory_optimize_pass has already been added
      to the analysis config before adding a new one, so
      that it is not added multiple times.
      test=develop
      
      * change map to unordered_map
      
      fix the forgotten part of cpu_quantize_pass_tester.cc
      
      test=develop
      
      * removed quantized attribute
      
      * fixed cpu_quantize_pass_tester and op attr comments
      
      test=develop
      
      * removed redundant line
      
      test=debug
      
      * removed gmock
      
      test=develop
      
      * fix after merge
      2579ade4
  21. 16 3月, 2019 1 次提交
  22. 15 3月, 2019 1 次提交
    • Q
      Support sync batch norm. (#16121) · 8ad672a2
      qingqing01 提交于
      * Support Sync Batch Norm.
      * Note, do not enable it in one device.
      
      Usage:
      
      build_strategy = fluid.BuildStrategy()
      build_strategy.sync_batch_norm = True
      binary = fluid.compiler.CompiledProgram(tp).with_data_parallel(
              loss_name=loss_mean.name,
              build_strategy=build_strategy)
      8ad672a2