JeVoisBase  1.22
JeVois Smart Embedded Machine Vision Toolkit Base Modules
Share this page:
Loading...
Searching...
No Matches

Simple DNN network running on NPU and invoked from the Khadas KSNN library in python. More...

Public Member Functions

 __init__ (self)
 [Optional] Constructor
 
 init (self)
 [Optional] JeVois parameters initialization
 
 freeze (self, doit)
 [Optional] Freeze some parameters that should not be changed at runtime
 
 load (self)
 [Required] Load the network from disk
 
 process (self, blobs)
 [Required] Main processing function: process input blobs through network and return output blobs blobs is a list of numpy arrays for the network's outputs Should return a tuple with (list of output blobs, list of info strings), where the info strings could contain some information about the network
 

Public Attributes

 net
 
 dataroot
 
 model
 
 library
 
 intensors
 

Detailed Description

Simple DNN network running on NPU and invoked from the Khadas KSNN library in python.

Author
Laurent Itti
Email:
itti@usc.edu
Address:
University of Southern California, HNB-07A, 3641 Watt Way, Los Angeles, CA 90089-2520, USA
Main URL:
http://jevois.org
Support URL:
http://jevois.org/doc
Other URL:
http://iLab.usc.edu
License:
GPL v3
Distribution:
Unrestricted
Restrictions:
None

Definition at line 24 of file PyNetKSNN.py.

Constructor & Destructor Documentation

◆ __init__()

PyNetKSNN.PyNetKSNN.__init__ (   self)

[Optional] Constructor

Definition at line 27 of file PyNetKSNN.py.

Member Function Documentation

◆ freeze()

◆ init()

PyNetKSNN.PyNetKSNN.init (   self)

[Optional] JeVois parameters initialization

Definition at line 32 of file PyNetKSNN.py.

◆ load()

◆ process()

PyNetKSNN.PyNetKSNN.process (   self,
  blobs 
)

[Required] Main processing function: process input blobs through network and return output blobs blobs is a list of numpy arrays for the network's outputs Should return a tuple with (list of output blobs, list of info strings), where the info strings could contain some information about the network

Definition at line 76 of file PyNetKSNN.py.

References PyNetORT.PyNetORT.inputs, PyNetURetinex.PyNetURetinex.inputs, Darknet.net, Yolo.net, ObjectRecognition< tiny_dnn::sequential >.net, ObjectRecognition< NetType >.net, PyNetKSNN.PyNetKSNN.net, PyNetOpenCV.PyNetOpenCV.net, PyClassificationDNN.PyClassificationDNN.net, PyDetectionDNN.PyDetectionDNN.net, and PyEmotion.PyEmotion.net.

Member Data Documentation

◆ dataroot

◆ intensors

◆ library

PyNetKSNN.PyNetKSNN.library

Definition at line 44 of file PyNetKSNN.py.

Referenced by PyNetKSNN.PyNetKSNN.load().

◆ model

◆ net


The documentation for this class was generated from the following file: