1. 15 11月, 2018 5 次提交
    • S
      add mkldnn prop_kind phase for inference-only case to pooling and activations (#14278) · 8a1eeec5
      Sylwester Fraczek 提交于
      * add is_test to pooling and activations
      
      add prop_kind support for layers activation. conv and pooling
      
      add a pass that sets is_test to true
      
      add transpiler version of is_test pass
      
      test=develop
      
      * patch test and pass
      
      test=develop
      
      * add pass to analyzer.h
      
      test=develop
      
      * add is_test attr description & pass only on mkldnn
      
      in:
      activation_op.cc
      batch_norm_op.cc
      conv_op.cc
      dropout_op.cc
      lrn_op.cc
      pool_op.cc
      sequence_pool_op.cc
      softmax_op.cc
      
      * fix is_test handling for activation pool and conv
      
      * change description of is_test for all layers again
      
      * remove GetAttr(use_mkldnn) from pass
      
      * rename correct_mkldnn_test_phase to is_test
      
      and remove dependency on MKLDNN
      test=develop
      
      * review fix magic number
      
      * two if(..)s into one
      
      * Check is_test once and pass mkldnn forward prop kind
      
      * dereference shared_ptr with * (without get())
      
      test=develop
      
      * add is_test_pass back
      
      test=develop
      8a1eeec5
    • C
      Add selu (#14415) · 82773477
      chengduo 提交于
      * add selu
      
      * use for range
      test=develop
      
      * add API
      test=develop
      
      * follow comment
      test=develop
      
      * update API.spec
      test=develop
      82773477
    • S
      rename mobilenet dir to mobilenet_depthwise_conv · d318583e
      Sylwester Fraczek 提交于
      test=develop
      d318583e
    • T
      rollback analyzer_seq_conv1_tester · 1d867805
      Tao Luo 提交于
      test=develop
      1d867805
    • Y
      Refine tester of TensorRT engine (#14390) · 9e6b1c5f
      Yiqun Liu 提交于
      * Refine the tester for MixedRTPredictor.
      test=develop
      
      * Enable the profiler in TensorRT engine.
      
      * Support the use of combined inference model in TensorRT unittest, and print the shape of feed targets.
      9e6b1c5f
  2. 14 11月, 2018 16 次提交
  3. 13 11月, 2018 17 次提交
  4. 12 11月, 2018 2 次提交