Upgrade to Pro — share decks privately, control downloads, hide ads and more …

TensorFlow for Mobile Developers

TensorFlow for Mobile Developers

Enrique López Mañas

October 25, 2017

More Decks by Enrique López Mañas

Other Decks in Technology


  1. Buzzwords classification Artificial intelligence Machine Learning The science of making

    machines smarts Building machines that can learn Neural Networks One of the many different algorithms in Machine Learning
  2. TensorFlow You can train: - Mac / Windows - GPU

    Server - GPU/TPU on Cloud Prediction: - Android - iOS - Raspberry
  3. Building with Android Studio Uses Bazel to build Set Bazel

    binary location in /tensorflow/examples/ android/build.gradle Add project in tensorflor/examples/android folder to Android Studio
  4. Building with Android Studio Installing Bazel first: Download from https://github.com/bazelbuild/bazel/releases

    Install instructions in https://docs.bazel.build/versions/master/install.html
  5. Building with Android Studio Download Android SDK (23) Download Android

    NDK (12b)
 (recommend it with Android SDK Manager)
  6. Building with Android Studio Run Bazel bazel build -c opt

    //tensorflow/examples/ android:tensorflow_demo
  7. Building with Android Studio OR… TensorFlow AAR from JCenter YUV

    -> RGB less efficient Object tracking not available
  8. TF Classify Uses Google Inception (v3) to label images Model

    easy to swap No “person label” Volume button up for statistics
  9. TF Detect - Draw bounding boxes around people - Useful

    to count objects - No training yet
  10. TF Style - Real time style transfer algorithm - Pick/mix

    different styles - Can train Magenta models
  11. TensorFlow Written in C++ Android uses Kotlin/Java?
 HowTo? Android

    inference Library https://github.com/tensorflow/tensorflow/tree/master/tensorflow/contrib/android
  12. Building for iOS Install requirements: - Xcode 8 - Command

    line tools (xcode-select install) - brew install automake - brew install lib tool - tensorflow/contrib/makefile_build_all_ios.sh (takes 20 minutes)