1. 04 3月, 2019 5 次提交
  2. 02 3月, 2019 1 次提交
    • T
      Update detection API add new check document (#15848) · 26e3842d
      tianshuo78520a 提交于
      * Update detection API add new check document
      
      * update API.spec
      
      * test=develop;add shanyi15 approved API.spec
      
      * test=develop;update PM check API.spec
      
      * check api.spec
      
      * test=develop
      
      * update API.spec
      
      * test=develop;update API.spec
      
      * update API.spec
      
      * cat API.spec
      
      * update documnent in api.spec
      
      * check python35 api.spec
      
      * update print_signatures md5 function
      
      * test=develop
      
      * update API.spec
      
      * test=develop;fix python3 API.spec diff
      
      * test=develop
      
      * test=develop
      
      * test=develop
      26e3842d
  3. 27 2月, 2019 1 次提交
  4. 26 2月, 2019 2 次提交
  5. 25 2月, 2019 2 次提交
  6. 24 2月, 2019 1 次提交
  7. 22 2月, 2019 1 次提交
  8. 21 2月, 2019 1 次提交
  9. 19 2月, 2019 5 次提交
  10. 12 2月, 2019 1 次提交
  11. 11 2月, 2019 3 次提交
  12. 01 2月, 2019 1 次提交
  13. 31 1月, 2019 1 次提交
  14. 30 1月, 2019 3 次提交
  15. 29 1月, 2019 7 次提交
  16. 28 1月, 2019 2 次提交
  17. 25 1月, 2019 2 次提交
  18. 24 1月, 2019 1 次提交
    • Y
      Add the CUDA kernel for beam_search op (#15020) · 3008fa12
      Yiqun Liu 提交于
      * Refine the beam_search op and test.
      
      * A basic CUDA implementation of beam_search for small batch_size.
      
      * Implement CUDA kernel for beam_search_op.
      
      * Use multiple CUDA threads in the same block to select the top beam.
      
      * Update the python api of beam_search op.
      
      * Enable extend function in CPU kernel of beam_search op.
      
      * Unify the CUDA codes.
      test=develop
      
      * Unify the CPU kernel of beam_search op.
      
      * Ensure the seletced items of beam_search_op's CPU kernel sorted by scores.
      
      * Update the description of beam_search in API.spec.
      
      * Enable the use of CUDA kernel in beam_search op.
      
      * Exclude the beam_search's CUDA unittest when there is no CUDA gpu, and delete some debuging statements.
      test=develop
      
      * Follow comments.
      test=develop
      
      * Call the CPU kernel for beam_search op when batch_size > 4.
      test=develop
      
      * Remove the except of is_empty op in PrepareData.
      test=develop
      3008fa12