2020 • 25:17
Bring your PyTorch models to Core ML and discover how you can leverage on-device machine learning in your apps. The PyTorch machine learning framework can help you create and train complex neural networks. After you build these models, you can convert them to Core ML and run them entirely on-device, taking full advantage of the CPU, GPU, and Neural Engine. Discover how the coremltools package can directly convert TorchScript models, and learn more about handling custom operations and conversion errors which may occur. To learn even more about Core ML Converters, we recommend the video "Get models on device using Core ML Converters" from WWDC20.
Speakers: Steve Berardi, Paul Curry