1. 11 11月, 2017 1 次提交
    • E
      Fixing duplicate struct name TensorSetConstant. (#5532) · 58b4c9af
      emailweixu 提交于
      TensorSetConstant struct is used both in math_function.cc and math_function.cu. Somehow the release version can correctly handle it. But in debug version, set_constant_with_place() in math_function.cu uses the TensorSetConstant in math_function.cc and causes crash.
      58b4c9af
  2. 08 11月, 2017 2 次提交
  3. 26 10月, 2017 1 次提交
  4. 18 10月, 2017 1 次提交
    • M
      MatMul operator (#4856) · 16489827
      Markus Kliegl 提交于
      * initial matmul operator
      
      Similar to np.matmul, but also has transpose_X and transpose_Y flags,
      and only supports tensors from rank 1 to 3 inclusive.
      
      For GPU, uses cublas?gemmStridedBatched. For CPU, uses
      cblas_?gemm_batch if available via MKL; otherwise a simple serial
      implementation that loops over the batch dimension is employed for now.
      16489827
  5. 16 10月, 2017 1 次提交
  6. 15 10月, 2017 1 次提交
  7. 14 10月, 2017 4 次提交
  8. 21 9月, 2017 1 次提交
  9. 19 9月, 2017 1 次提交
  10. 22 8月, 2017 2 次提交
  11. 21 8月, 2017 3 次提交
  12. 19 8月, 2017 1 次提交
  13. 14 8月, 2017 2 次提交
  14. 11 8月, 2017 2 次提交
  15. 10 8月, 2017 1 次提交
  16. 07 8月, 2017 2 次提交
  17. 03 8月, 2017 2 次提交