DeepLearningKit is an Open Source – with Apache 2.0 LicenceDeep Learning Framework for Apple’s iOS, OS X and tvOS available at

1. DeepLearningKit for iOS – Video Tutorial

2. DeepLearning for tvOS (Apple TV) – Video Tutorial

3. DeepLearningKit for OS X – Video Tutorial

4. Image Handling in DeepLearningKit – Tutorial

[Link to Tutorial – Image Handling in DeepLearningKit]

5. Goals of DeepLearningKit?

The goal is to support using pre-trained Deep Learning models on all Apple’s devices that have GPU(s). It is developed in Swift – to easily run on all platforms (iOS, OS X and tvOS) – and Metal – to efficiently use on-device GPU to ensure low-latency Deep Learning calculations. DeepLearningKit currently supports using (Deep) Convolutional Neural Networks (e.g. for image recognition) trained with the Caffe Deep Learning Framework (using this tool) but the long term goal is to support (perhaps with your help?) using deep learning models trained with the most popular Deep Learning frameworks (e.g. TensorFlow and Torch) as shown in figure below.


DeepLearningKit Resources

  1. Open source Code
  2. Tutorials
    1. Using DeepLearningKit with iOS for iPhone and iPad
  3. PublicationDeepLearningKit – an Open Source Deep Learning
    Framework for Apple’s iOS, OS X and tvOS developed in Metal and Swift
  4. Press Kit – DeepLearningKit logos in 932×522 pixels – JPG, PNG – 300×300 pixels PNG

Contribute to DeepLearningKit?

Check out this page if you want to contribute to DeepLearningKit