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 –
