1. 19 3月, 2020 4 次提交
  2. 18 3月, 2020 6 次提交
  3. 17 3月, 2020 5 次提交
    • W
      add cuda c++ doc. (#3207) · 52714b87
      Wilber 提交于
      add cuda c++ doc
      52714b87
    • W
      add cuda cxx demo (#3205) · f6461e39
      Wilber 提交于
      - 增加cuda c++ demo.
      - 考虑到检测模型尾部一般是multiclass_nms,该kernel为host,如果fetch kernel为cuda的话,则会在此处插入无用的io_copy(host->cuda),由于该原因,注释掉fetch的cuda kernel. 默认使用host的fetch kernel. 此处暗中进行的行为:每次predictor run完,都会默认把数据从cuda拷贝到cpu
      f6461e39
    • S
      [LITE][BM] support reduce and other ops, test=develop (#3199) · 7bf64f67
      Santa An 提交于
      * * support download bm_sdk, test=develop
      
      * [LITE][BM] add slice op
      
      * [LITE][BM] fix concat issue
      
      * [LITE][BM] support reduce full ops, test=develop
      
      * [LITE][BM] change test_resnet50 to change test_classify
      
      * [LITE][BM] add cast op
      
      * [LITE][BM] add reduce and other ops, test=develop
      
      * [LITE][BM] add reduce,cast and other ops, test=develop
      7bf64f67
    • W
      For cuda compilation products and ci (#3152) · 774b4652
      Wilber 提交于
      add cuda ci.
      
      Organize cuda compilation products.
      774b4652
    • M
      add sgd op (#3187) · 33c277e6
      mapingshuo 提交于
      * add sgd op, test=develop
      
      * test=develop
      33c277e6
  4. 16 3月, 2020 4 次提交
  5. 15 3月, 2020 2 次提交
  6. 14 3月, 2020 2 次提交
  7. 13 3月, 2020 3 次提交
  8. 12 3月, 2020 2 次提交
    • H
      [Core] Fix findar for Clang (#3160) · c7fb4138
      hong19860320 提交于
      * [Core] Fix findar for Clang
      test=develop
      
      * [CORE] Fix the missing of feed and fetch kernel when using light API to loade the optimized model
      test=develop
      c7fb4138
    • M
      add mean op (#3130) · b9273631
      mapingshuo 提交于
      * add mean op, test=develop
      
      * split forward and backward, test=develop
      b9273631
  9. 11 3月, 2020 1 次提交
  10. 10 3月, 2020 5 次提交
  11. 09 3月, 2020 6 次提交