1. 08 4月, 2020 1 次提交
  2. 29 2月, 2020 1 次提交
  3. 17 2月, 2020 1 次提交
  4. 14 2月, 2020 2 次提交
    • G
      Replace Softsign Eigen with c implementation (#2864) · e83d6b87
      GaoWei8 提交于
      * Replace Softsign Eigen with c implementation
      test=develop
      e83d6b87
    • Y
      [X86] Optimize gru and softmax (#2877) · 6b30c58a
      Yiqun Liu 提交于
      * Optimize softmax. When the input tensor is 2-D and axis is 1, there is no need to resize.
      
      * Optimize the gru, avoid calling Tensor::Slice.
      test=develop
      
      * Remove a std::vector in softmax.
      test=develop
      
      * Define CalculateSeqWidth to get the width of a sequence.
      test=develop
      6b30c58a
  5. 11 2月, 2020 2 次提交
  6. 07 2月, 2020 1 次提交
  7. 15 1月, 2020 1 次提交
  8. 06 1月, 2020 1 次提交
  9. 26 12月, 2019 1 次提交
  10. 25 12月, 2019 1 次提交
    • Y
      [X86] Polish the implementation of fc and imporve the unittest (#2656) · a0f01efa
      Yiqun Liu 提交于
      * Remove GEMM padding in fc_compute.
      test=develop
      
      * Write a common ParallelFor function to run the for loop in parallel.
      
      * Add the codes of padding GEMM back in fc.
      
      * Refine the code of fc when padding_weight is false to avoid the definition of temporary Tensor.
      
      * Refine the unit test of fc and add testing case of padding and parallel.
      test=develop
      
      * Enable more test cases in common fc unittest, including padding and parallel for x86 target.
      
      * Remove the fc test under kernels/x86.
      test=develop
      
      * Disable relu in test of fc for non-x86 target.
      test=develop
      
      * Change the eps of arm.
      test=develop
      a0f01efa
  11. 24 12月, 2019 1 次提交
  12. 19 12月, 2019 1 次提交
  13. 10 12月, 2019 1 次提交
  14. 08 12月, 2019 1 次提交
  15. 02 12月, 2019 2 次提交
  16. 28 11月, 2019 1 次提交
  17. 27 11月, 2019 1 次提交
  18. 26 11月, 2019 1 次提交
  19. 25 11月, 2019 1 次提交
  20. 22 11月, 2019 2 次提交
    • H
      update conv 2-pad to 4-pad (#2404) · b3a5fc1a
      HappyAngel 提交于
      * fix conv 2-pad to 4-pad
      
      * fix compute conv shape
      
      * fix pad, test=develop
      
      * change conv_depthwise_3x3s1_fp.cc name to conv3x3s1p01_depthwise_fp32.cc to distinguish between conv3x3s1_depthwise_fp32.cc
      
      * delete printf note in conv3x3s1, test=develop
      
      * delete printf note, test=develop
      
      * delete gem_sdot.h, test=develop
      
      it is coped from __gemm_sdot_meta_.h
      
      * update compute padding, test=develop
      
      * fix padding size, must be 2 or 4. test=develop
      
      * fix format in operators/conv_op.cc, test=develop
      
      * change #if 0 to #if 1, test=develop
      
      * put 2-pad to 4-pad in AttachImpl, test=develop
      
      * fix clang-format error inn tests/math/connv_compute_test, test=develop
      
      * fix x86 test result error, test=develop
      
      * add asymmetric padding test case in liite/tests/math/conv_compute.cc, test=develop
      
      * change paddings type to support dynamically modify, test=develop
      
      * fix x86 build error in connv_compute_test, test=develop
      
      * fix opencl build error, test=develop
      
      * fix oopencl build error, test=develop
      
      * fix  opencl/conv_compute build error, test=develop
      
      * fix  opencl/conv_compute build error, test=develop
      
      * fix format in kernels/opencl/conv_computte_ttest,test=develop
      
      * fix build error, test=develop
      
      fix build error in kernels/x86/conv_compute.h
      b3a5fc1a
    • H
      update pooling 2-padding to 4-padding (#2410) · 4bdb6171
      HappyAngel 提交于
      * fix pooling bug and speed
      
      * fix build error
      
      * delete VLOGin pool, test=develop
      
      * add openmp, test=develop
      
      * fix lite/kernels/arm/pool_compute_test basic_pooling compute error bug, test=develop
      
      * update pooling 2-pad to 4-pad, test=develop
      
      * fix 2-pad to 4-pad in operators/pool_op.h, AttachKernel will set param, so 2-pad to 4-pad funcs should put in AttachKernel. test=ddevellop
      
      * put 2-pad to 4-pad in AttachImpl, test=develop
      
      * according to reviews, fix some format error. test=develop
      
      * fix format errorr, add (). test=develop
      
      * change paddings type to support dynamically modify, test=develop
      
      * update padding type int other devices, test=develop
      
      * fix x8d build error on shared_ptr, test=ddevelop
      
      * fix formmat in operators pool_op.cc, test=develop
      4bdb6171
  21. 20 11月, 2019 3 次提交
  22. 19 11月, 2019 3 次提交
  23. 18 11月, 2019 3 次提交
  24. 16 11月, 2019 1 次提交
  25. 15 11月, 2019 1 次提交
    • J
      Add content-dnn ops (#2429) · 7f408ee8
      juncaipeng 提交于
      * add search_seq_depadding x86 and cuda
      * add match_matrix_tensor x86
      * add search_grnn x86, no test
      7f408ee8
  26. 14 11月, 2019 3 次提交
  27. 13 11月, 2019 2 次提交