Unable to Force-load TensorFlowLiteSelectTfOps.framework, created with Selective Build, in iOS

tanpengshi commented 5 months ago

IDE: Xcode 15 Platform: iOS17 TensorFlow version: r2.9

I am developing both iOS and Android apps that are running with TensorFlow Lite model. Because my model uses LSTM, I have to make use of TFSelectOps.

In addition, because the TensorFlowLiteSelectTFOps library is large in memory size, I have to do a selective build. After much effort, I have succeeded in making my TensorFlowLite model running smoothly on the Android app based on the selectively built libraries.

On the iOS however, I used a bazel build:

bash tensorflow/lite/ios/build_frameworks.sh \ --input_models=model1.tflite,model2.tflite \ --target_archs=x86_64,armv7,arm64

to generate the:

TensorFlowLiteSelectTfOps.framework
TensorFlowLiteC.framework

After that I edited the TensorFlowLiteSwift.podspec to include the framework:

Pod::Spec.new do |s|
  s.name             = 'TensorFlowLiteSwift'
  s.version          = '2.14.0'
  s.authors          = 'Google Inc.'
  s.license          = { :type => 'Apache' }
  s.homepage         = 'https://github.com/tensorflow/tensorflow'
  s.source           = { :git => 'https://github.com/tensorflow/tensorflow.git', :tag => "v#{s.version}" }
  s.summary          = 'TensorFlow Lite for Swift'
  s.description      = <<-DESC

  TensorFlow Lite is TensorFlow's lightweight solution for Swift developers. It
  enables low-latency inference of on-device machine learning models with a
  small binary size and fast performance supporting hardware acceleration.
                       DESC

  s.ios.deployment_target = '17.0'

  s.module_name = 'TensorFlowLite'
  s.static_framework = true

  tfl_dir = 'tensorflow/lite/'
  swift_dir = tfl_dir + 'swift/'

  s.default_subspec = 'Core'

  s.subspec 'Core' do |core|
    # Adjust the path to point to your custom frameworks
    core.vendored_frameworks = [
      'frameworks/TensorFlowLiteC.framework',
      'frameworks/TensorFlowLiteSelectTfOps.framework'
    ]

    core.source_files = swift_dir + 'Sources/*.swift'
    core.exclude_files = swift_dir + 'Sources/{CoreML,Metal}Delegate.swift'

    core.test_spec 'Tests' do |ts|
      ts.source_files = swift_dir + 'Tests/*.swift'
      ts.exclude_files = swift_dir + 'Tests/MetalDelegateTests.swift'
      ts.resources = [
        tfl_dir + 'testdata/add.bin',
        tfl_dir + 'testdata/add_quantized.bin',
      ]
    end
  end

  s.subspec 'CoreML' do |coreml|
    coreml.source_files = swift_dir + 'Sources/CoreMLDelegate.swift'
    coreml.dependency 'TensorFlowLiteSwift/Core', "#{s.version}"
  end

  s.subspec 'Metal' do |metal|
    metal.source_files = swift_dir + 'Sources/MetalDelegate.swift'
    metal.dependency 'TensorFlowLiteSwift/Core', "#{s.version}"

    metal.test_spec 'Tests' do |ts|
      ts.source_files = swift_dir + 'Tests/{Interpreter,MetalDelegate}Tests.swift'
      ts.resources = [
        tfl_dir + 'testdata/add.bin',
        tfl_dir + 'testdata/add_quantized.bin',
        tfl_dir + 'testdata/multi_add.bin',
      ]
    end
  end
end

I then do in the Podfile:

pod 'TensorFlowLiteSwift', :path => '../../local-podspecs/TensorFlowLiteSwift.podspec'

Then in terminal:

pod install

In my Other Linker Flags, i put: -force_load $(SRCROOT)/local-podspecs/frameworks/TensorFlowLiteSelectTfOps.framework/TensorFlowLiteSelectTfOps

But when I do build, i get lots of errors below:

FacialRecognition Undefined symbol: google::protobuf::TextFormat::PrintToString(google::protobuf::Message const&, std::1::basic_string<char, std::__1::char_traits, std::1::allocator>*)

Undefined symbol: google::protobuf::TextFormat::Parse(google::protobuf::io::ZeroCopyInputStream, google::protobuf::Message)

Undefined symbol: google::protobuf::DoubleValue::MergePartialFromCodedStream(google::protobuf::io::CodedInputStream*)

Undefined symbol: google::protobuf::DoubleValue::MergeFrom(google::protobuf::DoubleValue const&)

Undefined symbol: google::protobuf::DoubleValue::DoubleValue(google::protobuf::DoubleValue const&)

Undefined symbol: google::protobuf::MessageLite::ParseFromArray(void const*, int)

Undefined symbol: google::protobuf::MessageLite::ParseFromString(std::1::basic_string<char, std::__1::char_traits, std::1::allocator> const&)

Undefined symbol: google::protobuf::MessageLite::ParseFromCodedStream(google::protobuf::io::CodedInputStream*)