To get started with TensorFlow Lite on iOS, we recommend exploring the following example:
For an explanation of the source code, you should also read TensorFlow Lite iOS image classification.
This example app uses image classification to continuously classify whatever it sees from the device's rear-facing camera, displaying the top most probable classifications. It allows the user to choose between a floating point or quantized model and select the number of threads to perform inference on.
Add TensorFlow Lite to your Swift or Objective-C project
TensorFlow Lite offers native iOS libraries written in Swift and Objective-C. To get started quickly writing your own iOS code, we recommend using our Swift image classification example as a starting point.
The sections below demonstrate how to add TensorFlow Lite Swift or Objective-C to your project:
Podfile, add the TensorFlow Lite pod. Then, run
use_frameworks! pod 'TensorFlowLiteSwift'
BUILD file, add the
TensorFlowLite dependency to your target.
swift_library( deps = [ "//tensorflow/lite/experimental/swift:TensorFlowLite", ], )
objc_library( deps = [ "//tensorflow/lite/experimental/objc:TensorFlowLite", ], )
Import the library
For Swift files, import the TensorFlow Lite module:
For Objective-C files, import the umbrella header:
Or, the module if you set
CLANG_ENABLE_MODULES = YES in your Xcode project: