1. 06 3月, 2019 1 次提交
    • X
      Add Requantize OP (#15318) · a177d482
      xiaolil1 提交于
      * Enable INT8 ReQuantize OP
      test=develop
      
      * Clean code
      test=develop
      
      * Add comments
      test=develop
      
      * Revert "Clean code"
      test=develop
      
      This reverts commit a7a49b8a.
      
      * Modify requantize op test
      test=develop
      
      * fix requantize UT by moving public function to public test file.
      test=develop
      
      * Fix test fail due to file address change.
      test=develop
      
      * Change file address for requantize op.
      test=develop
      a177d482
  2. 04 3月, 2019 2 次提交
  3. 27 2月, 2019 2 次提交
  4. 26 2月, 2019 2 次提交
    • J
      - MKL-DNN pooling updated to set_prim_desc · c63f6b20
      Jacek Czaja 提交于
      - MKLDNN ops revisited
      
      - disabled softmax modifications
      
      - disabled elementwise_add
      
      - reverted LRN modifications
      
      - reverted SUM primitive
      
      - Partial reviing of softmax
      
      - Enable softmax
      
      - Softmax changes
      
      - LRN is back
      
      - LRN partially disabled
      
      - LRN is back
      
      - LRN fix
      
      - compilation fixes
      
      - Sum fixed(hopefully)
      
      - Enabling (partially) elementwise_add
      
      - Fixes to elemenwise_add
      
      - Lint fixes
      
      quantize fix
      
      - compilation fix
      
      test=develop
      
      Disabling pooling
      
      - Disabled quantize op
      
      test=develop
      c63f6b20
    • X
      Optimize INT8 DeQuantize Op with primitive reuse. · 70759d18
      xiaoli.liu@intel.com 提交于
      test=develop
      70759d18
  5. 25 2月, 2019 3 次提交
    • M
      Improve code reuse at MKL-DNN sum · 6ebe9877
      Michal Gallus 提交于
      test=develop
      6ebe9877
    • L
      Enable function coverage for U8/S8 ConvMKLDNNOpKernel · 4acc5220
      liangan1 提交于
      test=develop
      4acc5220
    • J
      [MKL-DNN] MKL-DNN specific Tensor modification (#15429) · dec9cf53
      Jacek Czaja 提交于
      * - Implemented draft of primitive desc keeping in Tensor
      
      test=develop
      
      - TransposeMKLDNNHandler::AcquireSrcMemory was reimplemented
      
      - Added nchw and nc formats setting for sake of compatiblity
      
      Fixed unit tests
      
      - Worakaround to problem with 5D data in conv
      
      - Added 3D and 1D MKL-DNN formats for name handles for tensor
      
      test=develop
      
      - Fix to UTs
      
      test=develop
      
      - Conv fp32 op was updated
      
      Cosmetic fixes
      
      test=develop
      
      - tensor mkldnn cosmetics
      
      test=develop
      
      - Moved most of mkl-dnn specific code from Tensor to mkl-dnn utils
      
      * - Lint fixes
      
      test=develop
      
      * - setting prim dec in Tensor , sets also layout to kMKLDNN
      
      test=develop
      
      * - Moved creation of prim desc totally out of Tensor
      
      test=develop
      
      * - Cosmetic fixes adter review
      
      test=develop
      dec9cf53
  6. 22 2月, 2019 1 次提交
  7. 21 2月, 2019 1 次提交
  8. 13 2月, 2019 1 次提交
  9. 29 1月, 2019 2 次提交