JeVoisBase  1.20
JeVois Smart Embedded Machine Vision Toolkit Base Modules
Share this page:
PyCoralClassify.PyCoralClassify Class Reference

Object recognition using Coral Edge TPU. More...

Public Member Functions

def __init__ (self)
 Constructor. More...
def process (self, inframe, outframe)
 JeVois main processing function. More...
def processGUI (self, inframe, helper)
 Process function with GUI output. More...

Public Attributes


Detailed Description

Object recognition using Coral Edge TPU.

This module runs an object classification deep neural network using the Coral TPU library. It only works on JeVois-Pro platform equipped with an Edge TPU add-on card. Classification (recognition) networks analyze a central portion of the whole scene and produce identity labels and confidence scores about what the object in the field of view might be.

This module supports networks implemented in TensorFlow-Lite and ported to Edge TPU/

Included with the standard JeVois distribution are:

  • MobileNetV3
  • more to come, please contribute!

See the module's constructor (init) code and select a value for model to switch network.

Object category names for models trained on ImageNet are at

Sometimes it will make mistakes! The performance of SqueezeNet v1.1 is about 56.1% correct (mean average precision, top-1) on the ImageNet test set.

This module is adapted from the sample code:

More pre-trained models are available at

Laurent Itti
YUYV 320 264 30.0 YUYV 320 240 30.0 JeVois PyClassificationDNN
880 W 1st St Suite 807, Los Angeles CA 90012, USA
Main URL:
Support URL:
Other URL:
GPL v3

Definition at line 53 of file

Constructor & Destructor Documentation

◆ __init__()

def PyCoralClassify.PyCoralClassify.__init__ (   self)


Definition at line 56 of file

References jevois.getNumInstalledTPUs().

Member Function Documentation

◆ process()

◆ processGUI()

Member Data Documentation

◆ interpreter

◆ labels

◆ model

◆ rgb

◆ threshold

◆ timer

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