1. 08 7月, 2019 1 次提交
    • T
      add mkldnn shapeblob cache clear strategy (#18513) · fe32879d
      Tao Luo 提交于
      * add mkldnn shapeblob cache clear strategy
      
      test=develop
      
      * refine with comments
      
      test=develop
      
      * make cache clear strategy more safey
      
      test=develop
      
      * add lock for GetShapeBlobSize
      
      test=develop
      fe32879d
  2. 05 7月, 2019 1 次提交
  3. 03 7月, 2019 2 次提交
  4. 02 7月, 2019 1 次提交
  5. 27 6月, 2019 1 次提交
    • L
      some fixes for int8 mobilenet_ssd tester (#18112) · 5fd68ac1
      lidanqing 提交于
      * some fixes for int8 mobilenet_ssd tester
      test=develop
      
      * change wrong data file name
      test=develop
      
      * change test images bin file from 200 images to 100 images
      
      * change directory existence to file existence during downloading
      test=develop
      
      * reuse download_data
      test=develop
      
      * run full dataset when iterations=0
      test=develop
      5fd68ac1
  6. 19 6月, 2019 2 次提交
  7. 16 6月, 2019 2 次提交
  8. 14 6月, 2019 1 次提交
    • L
      add Mobilienet ssd int8 analyzer tester (#18075) · 46625415
      lidanqing 提交于
      * add pascalvoc preprocess script and mobilenet-ssd analyzer_tester, wait 17737
      
      * change converting local dataset to downloading and converting tarfile
      test=develop
      
      * change the test data_path
      test=develop
      
      * change copyright (c) 2016 to copyright (c) 2019
      test=develop
      46625415
  9. 13 6月, 2019 2 次提交
  10. 11 6月, 2019 1 次提交
    • Update the Anakin interfaces for content-dnn and MLU (#17890) · bce259e5
      石晓伟 提交于
      * 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
      bce259e5
  11. 06 6月, 2019 2 次提交
  12. 29 5月, 2019 3 次提交
  13. 28 5月, 2019 1 次提交
    • L
      Improve mobilenetv2 INT8 performance by using INT8 relu as post-op (#17570) · 04b6c29e
      lidanqing 提交于
      * 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
      04b6c29e
  14. 24 5月, 2019 2 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
      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
  15. 22 5月, 2019 1 次提交
  16. 21 5月, 2019 2 次提交
  17. 15 5月, 2019 1 次提交
  18. 08 5月, 2019 1 次提交
  19. 07 5月, 2019 1 次提交
  20. 30 4月, 2019 1 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
  21. 23 4月, 2019 1 次提交
  22. 19 4月, 2019 1 次提交
  23. 17 4月, 2019 1 次提交
  24. 15 4月, 2019 3 次提交
  25. 12 4月, 2019 1 次提交
  26. 11 4月, 2019 1 次提交
  27. 09 4月, 2019 1 次提交
  28. 04 4月, 2019 2 次提交