Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 2 of 2 for handling (0.17 sec)

  1. tensorflow/c/eager/parallel_device/parallel_device.cc

            // (where the value starts on the host), without allowing other implicit
            // copies/broadcasts. Other implicit copies may be supported eventually,
            // but need special handling for gradients (gradient of copy-on is not
            // just copy-off but includes a sum) and consideration of performance.
            //
            // TODO(allenl): There may be smarter ways to do this copy in some
    C++
    - Registered: Tue Apr 30 12:39:09 GMT 2024
    - Last Modified: Wed Mar 29 22:05:31 GMT 2023
    - 18.3K bytes
    - Viewed (0)
  2. tensorflow/c/eager/tape.h

            }
          }
        } else {
          (*result)[id].push_back(output_gradients[i]);
        }
      }
      return absl::OkStatus();
    }
    
    // TODO(agarwal): use an automatic mechanism for handling None arguments to
    // gradient functions.
    //
    // Some gradient functions can accept None arguments for gradients. The
    // following maps the operation name to the indices at which the corresponding
    C
    - Registered: Tue Apr 30 12:39:09 GMT 2024
    - Last Modified: Tue Apr 02 12:40:29 GMT 2024
    - 47.2K bytes
    - Viewed (1)
Back to top