DEPTH_COMPUTE_DEVICE Class Reference

Lists the processors that can run the neural depth network. More...

Static Functions

def from_string (str, name)
 Converts a string to the corresponding DEPTH_COMPUTE_DEVICE enum value. More...
 

Detailed Description

Lists the processors that can run the neural depth network.

Enumerator
AUTO The processor that gives the best depth performance, currently the GPU (default).
GPU The GPU.
DLA Experimental. A Deep Learning Accelerator core of a Jetson AGX Orin or Orin NX with JetPack 6 (the Jetson Orin Nano has no DLA), which leaves the GPU to your application.
Only for sl.DEPTH_MODE.NEURAL_LIGHT; the network runs at its own precision, InitParameters.depth_precision is ignored and Camera.get_init_parameters() reports it as sl.DEPTH_PRECISION.LAST. Where it cannot be used, the depth runs on the GPU (sl.ERROR_CODE.CONFIGURATION_FALLBACK from Camera.open()).
PVA Experimental. The Programmable Vision Accelerator of a Jetson AGX Orin or Orin NX with JetPack 6 or 7.2, or of a Jetson Thor with JetPack 7.2 (the Jetson Orin Nano has none), which leaves the GPU to your application.
Only for sl.DEPTH_MODE.NEURAL_LIGHT; the network runs at its own precision, which Camera.get_init_parameters() reports (sl.DEPTH_PRECISION.LAST when it has no sl.DEPTH_PRECISION value). With another depth mode, or where it cannot be used, the depth runs on the GPU (sl.ERROR_CODE.CONFIGURATION_FALLBACK from Camera.open()).

Functions

◆ from_string()

def from_string (   str,
  name 
)
static

Converts a string to the corresponding DEPTH_COMPUTE_DEVICE enum value.

Parameters
name: The string representation of the DEPTH_COMPUTE_DEVICE enum value.
Returns
The corresponding DEPTH_COMPUTE_DEVICE enum value. If the string does not match any DEPTH_COMPUTE_DEVICE, DEPTH_COMPUTE_DEVICE.LAST is returned.