Apple announced at WWDC17 with iOS 11 CoreML. This allows you to integrate trained machine learning models into your iOS app. It has a minimizes memory footprint and power consumption and is optimized for on-device performance. In my talk I'll show how to train a very simple model and how to integrate it into a mobile app. Another demo will use InceptionV3 as pre-trained model and ARKit for augmented reality visualization.

1. Lars Gregori, SAP Hybris
November 25, 2017
Using A Trained Model
On Your Mobile Device

2. PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ 2
CoreML
▪ What is CoreML?
Train a model
▪ Train, convert, and add a model to an app.
Use a model
▪ Add an available model to an app.
Agenda

3. CoreML

4. PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ 4
A trained model is the result of applying a machine learning algorithm
to a set of training data.
The model makes predictions based on new input data.
CoreML
https://developer.apple.com/documentation/coreml
… integrates trained machine learning models into your app.

5. XOR example

6. PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ 6
0 xor 0 = 0
0 xor 1 = 1
1 xor 0 = 1
1 xor 1 = 0
XOR
if a != b

7. INTERNAL© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ 7
DEMO

8. Inception v3 example

9. PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ 9
arXiv:1512.00567 - Rethinking the Inception Architecture for Computer Vision
Inception v3

10. PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ 10
Inceptionv3.mlmodel

11. PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ 11
Inceptionv3.mlmodel

12. INTERNAL© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ 12

13. INTERNAL© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ 13
DEMO

14. Style transfer example

15. INTERNAL© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ 15https://developer.apple.com/documentation/coreml/converting_trained_models_to_core_ml

16. PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ 16
Style transfer with Torch & CoreML
https://blog.prismalabs.ai/diy-prisma-app-with-coreml-6b4994cc99e1

17. INTERNAL© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ 17
DEMO

18. PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ 18
Summary

19. PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ 19
Tensorflow Mobile
Tensorflow Lite
Android?

20. PUBLIC© 2017 SAP SE or an SAP affiliate company. All rights reserved. ǀ 20
CoreML
https://developer.apple.com/documentation/coreml
XOR example
https://amundtveit.com/2017/06/07/keras-deep-learning-with-apples-coremltools-on-ios-11-part-1/
Rethinking the Inception Architecture for Computer Vision.
https://arxiv.org/abs/1512.00567
Torch7 -> CoreML
https://github.com/prisma-ai/torch2coreml
Awesome Core ML Models
https://github.com/likedan/Awesome-CoreML-Models
Links

21. Thank you.
Lars Gregori, SAP Hybris
@choas
Hi Lars …

22. No part of this publication may be reproduced or transmitted in any form or for any purpose without the express permission of SAP SE or an SAP affiliate company.
The information contained herein may be changed without prior notice. Some software products marketed by SAP SE and its distributors contain proprietary software components
of other software vendors. National product specifications may vary.
These materials are provided by SAP SE or an SAP affiliate company for informational purposes only, without representation or warranty of any kind, and SAP or its affiliated
companies shall not be liable for errors or omissions with respect to the materials. The only warranties for SAP or SAP affiliate company products and services are those that are
set forth in the express warranty statements accompanying such products and services, if any. Nothing herein should be construed as constituting an additional warranty.
In particular, SAP SE or its affiliated companies have no obligation to pursue any course of business outlined in this document or any related presentation, or to develop or release
any functionality mentioned therein. This document, or any related presentation, and SAP SE’s or its affiliated companies’ strategy and possible future developments, products, and/
or platform directions and functionality are all subject to change and may be changed by SAP SE or its affiliated companies at any time for any reason without notice. The information
in this document is not a commitment, promise, or legal obligation to deliver any material, code, or functionality. All forward-looking statements are subject to various
risks and uncertainties that could cause actual results to differ materially from expectations. Readers are cautioned not to place undue reliance on these forward-looking statements,
and they should not be relied upon in making purchasing decisions.
SAP and other SAP products and services mentioned herein as well as their respective logos are trademarks or registered trademarks of SAP SE (or an SAP affiliate company)
in Germany and other countries. All other product and service names mentioned are the trademarks of their respective companies.
See http://global.sap.com/corporate-en/legal/copyright/index.epx for additional trademark information and notices.
© 2017 SAP SE or an SAP affiliate company. All rights reserved.