1. 19 12月, 2018 9 次提交
    • T
      MKLDNN residual connection fuse: fixing accuracy problem (#14874) · e9eee0de
      Tomasz Patejko 提交于
      * MKLDNN residual connection fuse: conv op reused
      
      test=develop
      
      * MKLDNN residual connection fuse: added prints for checking fuse
      
      test=develop
      
      * MKLDNN residual connection fuse: add more prints
      
      test=develop
      
      * MKLDNN residual connection fuse: add hash function. test=develop
      
      * MKLDNN residual connection fuse: add hash to elementwise_add
      
      test=develop
      
      * MKLDNN residual connection fuse: add more hashes. test=develop
      
      * MKLDNN residual connection fuse: added hashes to relu
      
      test=develop
      
      * MKLDNN residual connection fuse: do not fuse when fuse_relu is on
      
      * MKLDNN residual connection fuse: check if fuse_relu attribute is set
      
      test=develop
      
      * MKLDNN residual connection fuse: comment out some printouts
      
      * MKLDNN residual connection fuse: remove unused functions in the pass code
      
      * MKLDNN residual connection fuse: delete commented hashes and printouts
      
      * MKLDNN residual connection fuse: remove unnecessary includes. test=develop
      e9eee0de
    • T
      clean code and remove unused files · d53c4756
      tensor-tang 提交于
      test=develop
      d53c4756
    • T
      add more impls of lstm and gru and fix build on win · c187a7c6
      tensor-tang 提交于
      test=develop
      c187a7c6
    • T
      fix lstm and gru jitcode · 83d075aa
      tensor-tang 提交于
      test=develop
      83d075aa
    • T
      add more impls of sigmoid and vtanh · f332f589
      tensor-tang 提交于
      f332f589
    • M
      Enable mul operator for a ngraph engine (#14801) · 9035bb81
      mozga-intel 提交于
      * Enable mul operator for a ngraph
      test=develop
      
      * Enable activation ops test
      test=develop
      
      * Remove unused line
      test=develop
      9035bb81
    • T
      enable layer norm intrinsic code · ea259c63
      tensor-tang 提交于
      ea259c63
    • G
      Add size enforce (#14919) · b849157e
      gongweibao 提交于
      b849157e
    • J
      [MKL-DNN ]Added transpose/transpose2 Op (#14872) · aa6e9c30
      Jacek Czaja 提交于
      * - Added transpose MKLDNN Op
      - Few basic UT works
      - Added 1D transpose
      - implementing generic mem desc for MKLDNN transpose
      - Modified trnaspose op to support  more dimensional data eg. 5,6..10
      - Added is_test attribute to transpose op
      
      test=develop
      
      * - Added support for MKLDNN::memory::format::any for Transpose MKLDNN op
      
      test=develop
      
      * - Additional transpose mkldnn op correction to mkldnn layout
      
      test=develop
      
      * Cosmetic fixes
      
      test=develop
      
      * - Removed const_cast to obey coding standard
      
      test=develop
      aa6e9c30
  2. 18 12月, 2018 18 次提交
  3. 17 12月, 2018 13 次提交