Visual Recognition with Anki Cozmo and TensorFlow Deployed on IBM Cloud via Kubernetes and Apache OpenWhisk December 2017 Niklas Heidloff Developer Advocate, IBM @nheidloff Ansgar Schmidt Developer Advocate, IBM @ansi
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Visual Recognition with Anki Cozmo and TensorFlow
Deployed on IBM Cloud via
Kubernetes and Apache OpenWhisk
December 2017
Niklas Heidloff Developer Advocate, IBM
@nheidloff
Ansgar Schmidt Developer Advocate, IBM
@ansi
Setup
Cozmo recognizes different Toys
Cozmo’s View:
@nheidloff @ansi
Dem
o
Demo
@nheidloff @ansi
Video
Dem
o
Demo
@nheidloff @ansi
Cozmo’s View
Dem
o
Demo
@nheidloff @ansi
Cozmo’s Brain
Training
Training – Circle around Toys and take Pictures
@nheidloff @ansi
Training
Training – Architecture
MobileNet
@nheidloff @ansi
Classification
Classification – Architecture
@nheidloff @ansi
Classification
Web App to test the extended MobileNet Model
@nheidloff @ansi
Resources
Resources
• https://github.com/nheidloff/visual-recognition-for-cozmo-with-tensorflow
• https://github.com/anki/cozmo-python-sdk • https://codelabs.developers.google.com/codelabs/
tensorflow-for-poets
• https://www.ibm.com/cloud • https://openwhisk.apache.org
Related Documents
