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 https://github.com/jevois/jevoisbase/blob/master/share/opencv-dnn/classification/synset_words.txt

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: https://github.com/google-coral/pycoral/blob/master/examples/classify_image.py

More pre-trained models are available at https://coral.ai/models/