View Source Evision.IPCHandle.Local (Evision v0.2.9)

Represents a local CUDA handle for sharing data allocated on the same CUDA device within the same OS processes.

• :handle, a pointer to the memory that can be accessed within the same OS process.

  when :type is :cuda_ipc, is a pointer to the memory that can be accessed by other OS processes via CUDA IPC.

• :step, the number of bytes between two consecutive rows.

  When there are no gaps between successive rows, the value of step is equal to the number of columns times the size of the data type.

• :rows, the number of rows.

• :cols, the number of columns.

• :channels, the number of channels.

• :type, the data type.

• :device_id is the CUDA device ID that the memory is allocated on.