So far, we have learned how to convert a TensorFlow model into tflite format and performed inference on an Android phone and Raspberry Pi. In this section, we will use the tflite model and perform inference on an iPhone. Object detection on iPhone or iPad can follow two different paths, as discussed in the following subsections.
Object detection on iPhone using TensorFlow Lite and Create ML
TensorFlow Lite conversion model for iPhone
In this section, we will describe how to use a tflite model on iPhone for object detection. For details, please refer to the steps outlined on the following GitHub page: https://github.com/tensorflow/examples/tree/master/lite/examples/image_classification/ios.
Essentially, the procedure can be...