• M
    Conv Shift Operator (#4591) · a281b383
    Markus Kliegl 提交于
    * conv_shift_op: initial implementation using Eigen
    
    Limitations:
    - both gradient outputs must be specified and are always computed
    - explicit for loops => could be optimized in various ways
      (e.g., different memory layout)
    
    * conv shift - gradient fixes
    
    fix case when not all output gradients desired
    
    * conv shift: minor cleanup
    
    * conv shift - more minor cleanup
    
    * conv shift: clean up & initial GPU implementation
    
    * fix rebase issue
    a281b383
conv_shift_op.h 1.1 KB