To get started with TensorFlow Lite on iOS, we recommend exploring the following example:
iOS image classification 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. Start writing your own iOS code using the 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'
There are stable releases, and nightly releases available for both
TensorFlowLiteObjC pods. If you do not specify a
version constraint as in the above examples, CocoaPods will pull the latest
stable release by default.
You can also specify a version constraint. For example, if you wish to depend on version 2.0.0, you can write the dependency as:
pod 'TensorFlowLiteSwift', '~> 2.0.0'
This will ensure the latest available 2.x.y version of the
pod is used in your app. Alternatively, if you want to depend on the nightly
builds, you can write:
pod 'TensorFlowLiteSwift', '~> 0.0.1-nightly'
From 2.4.0 version and latest nightly releases, by default GPU and Core ML delegates are excluded from the pod to reduce the binary size. You can include them by specifying subspec:
pod 'TensorFlowLiteSwift', '~> 0.0.1-nightly', :subspecs => ['CoreML', 'Metal']
This will allow you to use the latest features added to TensorFlow Lite. Note
that once the
Podfile.lock file is created when you run
pod install command
for the first time, the nightly library version will be locked at the current
date's version. If you wish to update the nightly library to the newer one, you
pod update command.
For more information on different ways of specifying version constraints, see Specifying pod versions.
BUILD file, add the
TensorFlowLite dependency to your target.
swift_library( deps = [ "//tensorflow/lite/swift:TensorFlowLite", ], )
objc_library( deps = [ "//tensorflow/lite/objc:TensorFlowLite", ], )
Alternatively, you can use C API or C++ API
# Using C API directly objc_library( deps = [ "//tensorflow/lite/c:c_api", ], ) # Using C++ API directly objc_library( deps = [ "//third_party/tensorflow/lite:framework", ], )
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: