Object detection on Android phones using TensorFlow Lite

The steps required to deploy the TensorFlow lite converted model will be described in this section. Alternatively, you can follow the instructions at https://github.com/tensorflow/examples/tree/master/lite/examples/image_classification/android to build a sample app. A detailed flow chart regarding object detection on Android phones is as follows:

We need two files:

• The TensorFlow Lite converted file in.tflite form
• An updated labelmap .txt file showing the class

The .tflite file comes directly from Google Colab if we export it, as explained in the TensorFlow Object Detection API – toco section. The lablemap.txt file comes from the label_map.pbtxt file by listing only the names of the class.

The sample files can be found at the following GitHub page: https://github.com/PacktPublishing/Mastering-Computer-Vision-with...