1. 22 11月, 2021 1 次提交
    • A
      Add isclose op (#37135) · d2200e97
      andyjpaddle 提交于
      * add isclose op, test=develop
      
      * add isclose op, test=develop
      
      * add isclose api, test=develop
      
      * rm useless code
      
      * rm useless code
      
      * update python api of isclose
      
      * add some unittest of isclose op, test=develop
      d2200e97
  2. 03 3月, 2021 1 次提交
  3. 19 10月, 2020 1 次提交
    • H
      Allclose op (#27891) · d4668938
      huangxu96 提交于
      * Still has bugs.
      
      * Fixed allclose_op bug, which cannot deal with some cases of fp64 inputs.
      
      * improved CUDA kernel performance.
      
      * Changed CUDA code.
      
      * Fixed a bug in cuda kernel which cannot deal with large dimension input, and added an unittest for it.
      
      * Add a test case for float32 input.
      d4668938
  4. 04 4月, 2020 1 次提交
    • Z
      Add allclose_op (#23335) · 56b50c97
      Zhen Wang 提交于
      * Add allclose Op, and its function is analogous to numpy.allclose. It returns True if two tensors are elementwise equal within a tolerance.
      56b50c97
  5. 30 5月, 2018 2 次提交
  6. 14 5月, 2018 1 次提交
  7. 07 4月, 2018 1 次提交
  8. 07 3月, 2018 2 次提交
  9. 06 3月, 2018 2 次提交
  10. 15 2月, 2018 1 次提交
    • Y
      Update tensor_util.h (#8422) · cfffb1a3
      Yi Wang 提交于
      * Update tensor_util.h
      
      * Update with moved TensorDesc
      
      * Fix tensur_utils.cu
      
      * Update
      
      * Update
      
      * Update
      
      * Update
      
      * Make tensor_util.cu a symbolic link
      cfffb1a3
  11. 10 2月, 2018 2 次提交
  12. 07 2月, 2018 1 次提交
  13. 06 2月, 2018 2 次提交
  14. 01 2月, 2018 1 次提交
  15. 31 1月, 2018 1 次提交
  16. 30 1月, 2018 1 次提交