1. 23 12月, 2019 1 次提交
    • H
      [lite][arm]add conv relu6 and leaky_relu in conv_dw_3x3s2, test=develop (#2618) · d4739621
      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
      
      * fix ccompute shape error in ooperators/conv_op.h, test=develop
      
      * add conv_reelu6 and conv leaky_relu in conv_3x3s1_direct
      
      * add conv_relu6 in c1, c2, c4,test=develop
      
      * fix conflict in conv_bloock_utils.h, test=develop
      
      * add relu6 and leankyrelu in conv_3x3s1_dw
      
      * add conv_3x3s1px_dw relu6 and leaky_relu fusion, test=develop
      
      * fix conflict in tests/math/conv_compute_arm, test=develop
      
      * fix build error in winograd arm, test=develop
      
      * channge act_param as pointer in conv_block_tuils.h, test=develop
      
      * fix winograd in no equal 4-padding compute error, test=develop
      
      * add conv relu6 and leaky_relu in conv_dw_3x3s2, test=develop
      
      * fix format, test=develop
      
      * fix format in conv_block_utils, test=develop
      
      * move updatePadding from conv_op.cc to conv_op.h, test=develop
      
      * fix format conv_op.h, test=develop
      
      * fix buuilde error in conv_oop.h, test=develop
      
      * remove flag_relu parameter in conv_3x3_depthwise, test=develop
      d4739621
  2. 17 12月, 2019 1 次提交
  3. 22 11月, 2019 1 次提交
    • H
      add NHWC NCHW transform, test=develop (#2381) · 6b3c341f
      HappyAngel 提交于
      * add nhwc to nchw
      
      * add layout in funcs
      
      * change layout as extra, test=develop
      
      * change make, test=develop
      
      * use template class method to update layout NNCHHW and NHWC transform, test=develop
      
      * fix cmake error, set layout to extra, test=develop
      
      * fix test_layout_compute_arm test, its extra
      
      * layout is extra, test=develop
      
      * fix error in kernels/arm/layout_comput.cc when register kernel, DataLayout must be NCHW, test=develop
      
      * delete extra note, test=develop
      
      * delete extra test
      
      * delete layout_test, test=develop
      
      , its in tests/math/layout_comput_test
      
      * delete extrat test, test=develop
      6b3c341f
  4. 17 10月, 2019 1 次提交
    • H
      speedup fp32 depthwise conv · 2f6d5f9e
      HappyAngel 提交于
      * update con_dw
      
      * update
      
      * add conv_depthwise_3x3s1.cc and conv_depthwise_3x3s2.cc
      
      * add conv_depthwise_3x3s1_fp32 and conv_depthwise_3x3s2_fp32
      
      * add new conv_dw
      
      * only support conv_dw pad=0, 1
      
      * add conv_dw_s1 conv_dw_s2 fp32
      
      *     //conv2_func _impl2{nullptr};
      update conv_dw, add conv_3x3s1 and conv_3x3s2, pad=[0,1]
      
      * fix format, test=develop
      
      * fix formmat, test=develop
      2f6d5f9e