TF Mobile in iOS apps

TensorFlow enables support for iOS apps by following these steps:

1. Include TF Mobile in your app by adding a file named Profile in the root directory of your project. Add the following content to the Profile:

target 'Name-Of-Your-Project'
       pod 'TensorFlow-experimental'

2. Run the pod install command to download and install the TensorFlow Experimental pod.
3. Run the myproject.xcworkspace command to open the workspace so you can add the prediction code to your application logic.

Note

To create your own TensorFlow binaries for iOS projects, follow the instructions at this link: https://github.com/tensorflow/tensorflow/tree/master/tensorflow/examples/ios

Once the TF library is configured in your iOS project, you can call the TF model with the following four steps:

1. Load the model:

PortableReadFileToProto(file_path, &tensorflow_graph);

2. Create a session:

tensorflow::Status s = session->Create(tensorflow_graph);

3. Run the prediction or inference and get the outputs:

std::string input_layer...