Tensorflow IoT - 1 Wk coding challenge
- 1. Tensorflow for IoT GEETA CHAUHAN JUNE, 2017
- 2. Agenda Build Deep Learning App in a week Deep Learning basics Tensorflow for IoT Optimizations for IoT Common Problem Solutions Use Cases for IoT Look into the Future References
- 3. Intelligent Door Welcome Sara Good Kitty
- 4. What is Deep Learning? AI Neural Networks composed of many layers Learn like humans Automated Feature Learning Layers are like Image Filters
- 5. Tensorflow Android Things Add Tensorflow Inferencing library Create Inference object, load model feed() image, run() to predict fetch() to get classification result
- 6. Transfer Learning Transfer Learning – New Classifier Inception V3
- 7. Demo Intel Edison + Seed Studio Kit Raspberry Pi + Pi Camera
- 8. Tensorflow IoT Pipeline Inference on DeviceTrain Model in Cloud
- 9. What is Deep Learning? AI Neural Networks composed of many layers Learn like humans Automated Feature Learning Layers are like Image Filters
- 10. Optimizations Graph Transform Tool Freeze graph (variables to constants) Quantize weights (20 M weights for IV3) Quantization (32 bit float → 8 bit float) Memory Mapping Inception v3 93 MB → 1.5 MB
- 11. Common Problem Solutions Tensorboard is your friend – X-Ray vision Image size mismatch for the input tensor Output classifier specify correct number of classes from your model Model too large – Load in memory Missing ops -- Graph transform tool Device heating up under heavy processing load Split the model, do part detection on device, rest in cloud Reduce the frequency eg only do on movement detection
- 12. Cucumber Sorter
- 13. Caltrain Rider Realtime Caltrain arrival prediction Audio Visual pipeline on Raspberry pi Image classification for Caltrains
- 14. And Some More … Self Driving Car Wearable assistant for Blind (Horus) Smart cameras, smart door lock Human line counter Real time exercise score on smart watch Creative Arts, Music Generators Intelligent Robots
- 15. Era of AI First Billions of connected devices Intelligence at the Edge Increasing Computation power Edison: 500 MHz, 1 GB RAM RPi3: 1.2 GHz Quad-core Deep neural networks running on the IoT device Local inferencing → compressed insights to cloud
- 16. Look into the Future Hardware: Neural Network Chips Intel Fathom Neural Stick Nvidia Jetson
- 17. References Tensorflow for Android Things Sample Tensorboard hands-on Graph Transform Tool Tensorflow for Poets (Transfer learning) Tensorflow for Poets2 (Optimizations for Mobile/IoT) Cucumber Farmer Deep Learning Story Caltrain Rider story Intel Fathom Neural Stick Nvidia Jetson Google’s latest “One Model to Learn them all” paper