1. 05 4月, 2020 1 次提交
    • Y
      [LITE][OPENCL] Fix opencl backend: Free opencl resources; Fix... · 296bda4d
      Yuan Shuai 提交于
      [LITE][OPENCL] Fix opencl backend: Free opencl resources; Fix AddKernel/GetKernel, program and all opencl kernels (#3344)
      
      * [DONT MERGE] Fix opencl backend.
      
      * [LITE][OPENCL] Fix kernels overlapped when add/get for kernels of mnasnet/yolonano. test=develop
      
      * remove useless. test=develop
      
      * add all image kernels for Get/Add kernel. test=develop
      
      * add all image kernels for Get/Add kernel. test=develop
      
      * fix buffer kernels of opencl. test=develop
      
      * fix release opencl. test=develop
      296bda4d
  2. 04 4月, 2020 1 次提交
  3. 03 4月, 2020 4 次提交
  4. 02 4月, 2020 2 次提交
  5. 01 4月, 2020 2 次提交
  6. 30 3月, 2020 2 次提交
  7. 27 3月, 2020 3 次提交
  8. 26 3月, 2020 2 次提交
  9. 25 3月, 2020 2 次提交
  10. 24 3月, 2020 5 次提交
  11. 23 3月, 2020 2 次提交
  12. 22 3月, 2020 1 次提交
  13. 20 3月, 2020 1 次提交
  14. 18 3月, 2020 3 次提交
  15. 17 3月, 2020 5 次提交
    • W
      add cuda c++ doc. (#3207) · fcc6b2da
      Wilber 提交于
      add cuda c++ doc
      fcc6b2da
    • W
      add cuda cxx demo (#3205) · 9098da7c
      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
      9098da7c
    • S
      [LITE][BM] support reduce and other ops, test=develop (#3199) · 64a796d1
      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
      64a796d1
    • W
      For cuda compilation products and ci (#3152) · ca2481e6
      Wilber 提交于
      add cuda ci.
      
      Organize cuda compilation products.
      ca2481e6
    • M
      add sgd op (#3187) · 92204e52
      mapingshuo 提交于
      * add sgd op, test=develop
      
      * test=develop
      92204e52
  16. 16 3月, 2020 4 次提交