1. 21 1月, 2019 2 次提交
    • F
      add python inference api (#15248) · d60751fb
      flame 提交于
      add python inference api
      d60751fb
    • D
      Memory optimization of depthwise conv op and group norm op (#15313) · 9f8f0fc2
      Dun 提交于
      * mem opt
      
      * test=develop
      
      * test=develop
      
      * test=develop
      
      * test=develop
      
      * test=develop
      
      * test=develop
      
      * test=develop
      
      * refine code  test=develop
      
      * refine code  test=develop
      
      * refine code  test=develop
      
      * refine code  test=develop
      
      * refine with cub test=develop
      
      * fix mkldnn test && remove comments && test=develop
      
      * polish code && test=develop
      
      * add only_forward test && test=develop
      9f8f0fc2
  2. 18 1月, 2019 2 次提交
    • Z
      Tree conv op (#15217) · e2ba9668
      zhaozhehao 提交于
      * refactor tree2col operator with new memory mechanism test=develop
      
      * test=develop
      
      * test=develop
      
      * Modified API according to panyx0718 test=develop
      
      * fix API change according to heavengate test=develop
      
      * Modify API comment test=develop
      e2ba9668
    • C
      speed fetch_feed_test (#15383) · 958ca2c7
      chengduo 提交于
      test=develop
      958ca2c7
  3. 16 1月, 2019 4 次提交
  4. 15 1月, 2019 5 次提交
  5. 14 1月, 2019 5 次提交
  6. 13 1月, 2019 2 次提交
  7. 11 1月, 2019 2 次提交
  8. 10 1月, 2019 4 次提交
    • X
      Conv int8 residual (#15145) · 8f17c714
      xiaolil1 提交于
      * Enable basic MKL-DNN INT8 Conv OP
      test=develop
      
      * Modify test case
      test=develop
      
      * Clean unittest code
      test=develop
      
      * Fix test
      test=develop
      
      * Modify test
      test=develop
      
      * Enable MKL-DNN INT8 Conv with Relu Fusion OP
      test=develop
      
      * Enable INT8 Conv with residual fusion OP
      test=develop
      
      * Modify code.
      test=develop
      
      * Modify basic INT8 Conv
      test=develop
      
      * Modify Conv.
      test=develop
      
      * fix style
      test=develop
      
      * Fix style
      test=develop
      
      * Fix test
      test=develop
      
      * Modify code.
      test=develop
      
      * Fix test
      test=develop
      8f17c714
    • C
      open compare_reduce_and_allreduce test (#15258) · 0e178033
      chengduo 提交于
      test=develop
      0e178033
    • W
      [Feature] support mix precision training for resnet (#14899) · fd854183
      Wu Yi 提交于
      * clip softmax for fp16
      
      * updates
      
      * fuse xent support fp16 test=develop
      
      * wip
      
      * wip
      
      * add simple row reduce
      
      * wip fp16 accurate softmax
      
      * add accurate softmax kernel for fp16 test=develop
      
      * update test=develop
      
      * fix cpu build test=develop
      
      * update api.spec test=develop
      
      * follow comments test=develop
      
      * fix build test=develop
      
      * fix trt build test=develop
      
      * fix inference build test=develop
      
      * fix merge test=develop
      
      * update test=develop
      
      * try fix build test=develop
      
      * fix build test=develop
      
      * rename real_exp test=develop
      
      * fortest
      
      * remove hacky kernels test=develop
      
      * clean up test=develop
      fd854183
    • F
      Add python ir graph API (#14917) · fb63cd89
      flame 提交于
      fb63cd89
  9. 09 1月, 2019 7 次提交
  10. 08 1月, 2019 4 次提交
  11. 07 1月, 2019 3 次提交
    • T
      add seqpool concat unit test · 31663640
      tensor-tang 提交于
      31663640
    • X
      Conv int8 relu (#15130) · c8f101e5
      xiaolil1 提交于
      * Enable basic MKL-DNN INT8 Conv OP
      test=develop
      
      * Modify test case
      test=develop
      
      * Clean unittest code
      test=develop
      
      * Fix test
      test=develop
      
      * Modify test
      test=develop
      
      * Enable MKL-DNN INT8 Conv with Relu Fusion OP
      test=develop
      
      * Modify basic INT8 Conv
      test=develop
      
      * fix type
      test=develop
      
      * Modify test
      test=develop
      c8f101e5
    • X
      update api · 0d0bc612
      Xin Pan 提交于
      test=develop
      0d0bc612