Custom vision

Azure Custom Vision, Artificial Intelligence, AI, ML MIcrosoft Technology stack

1. Custom Vision Service Global AI Bootcamp Pushkar Saraf 1

2. Cognitive Services Computer Vision vs Custom Vision how they differ Which scenarios to chose for either. Time to Market Taking it to the EDGE Overview Project Brainwave and FPGA’s Intel ComputeStick for edge devices Agenda

3. Azure Cognitive Services Emotion Speaker Recognition Speech Custom Recognition Computer Vision Face Video Search Speech Language Knowledge Vision Linguistic Analysis Language Understanding Bing Spell Check Entity Linking Knowledge Exploration Academic Knowledge Bing Image Search Bing Video Search Bing Web Search WebLM Text Analytics Recommendations Bing Autosuggest Bing News Search Translator Bot Framework Cognitive Services

4. What is it? An API What does it do ? Classification | Object Detection What do I need to know ? Object’s [] Model Custom Vision

5. Custom Vision Service Export to Container (export DockerFile + model +service) and to ONNX S0 tier expanded to up to 250 tags and 50,000 images.

6. Upload Images Upload your own labeled images, or use Custom Vision Service to quickly tag any unlabeled images. Train Use your labeled images to teach Custom Vision Service the concepts you want it to learn. Evaluate Use simple REST API calls to quickly tag images with your new custom computer vision model. Active learning Images evaluated through your custom vision model become part of a feedback loop you can use to keep improving your classifier. Custom Vision Service

7. Upload Images Upload your own labeled images, or use Custom Vision Service to quickly tag any unlabeled images. Train Use your labeled images to teach Custom Vision Service the concepts you want it to learn. Evaluate Use simple REST API calls to quickly tag images with your new custom computer vision model. Active learning Images evaluated through your custom vision model become part of a feedback loop you can use to keep improving your classifier. Custom Vision Service

8. How it Works

9. FACT: There is a lot of work.

10. Create a Project

11. Add Images

12. Upload Images

13. Test Results

14. Export models as packages Announcement: https://aka.ms/cvsexport Sample: https://github.com/Azure-Samples/cognitive-services-ios-customvision-sample Xamarin port: https://github.com/Xamarin/ios-samples/tree/master/ios11/CoreMLAzureModel

15. Best Practices for using Custom Vision Use at least 30 images for each tag Images should be the focus of the picture Use sufficiently diverse images and backgrounds (ex: cats with red background and dogs with blue background) Train with images that are similar in {quality, resolution, lighting, etc.} to the images that will be used in prod Supports Microsoft accounts (MSA) and AAD

16. Resources: Custom Vision Service Get started at http://customvision.ai Programmatic API access using C# (Python and Node SDKs coming soon): https://github.com/Microsoft/Cognitive-CustomVision-Windows

17. Project BrainWave : FPGA’s Get started at http://customvision.ai Programmatic API access using C# (Python and Node SDKs coming soon): https://github.com/Microsoft/Cognitive-CustomVision-Windows

18. Brainwave Stack

19. FPGA’s Block

20. Container Registry Machine Learning (Model Management) Azure VM Raspibian Docker for Linux AML Module Picture Jpeg File Result Serialized Data Data Check & Determination HTTP Generate Result SenseHat Docker Apps AML Package for Computer Vision Camera Extending The AI to edge

21. Going Beyond 4  teraflops GTX 1080 : 9 teraflops Intel FPGA’s 39 Tera flops 1 Teraflop = 10^2 computations 1 Teraflop = 1000 GFlops 1 Teraflop = 31688 years compare to single compute per/sec calculations

22. Get connected… http://www.puneusergroup.org http://www.facebook.com/puneusergroup http://twitter.com/puneusergroup http://www.linkedin.com/groups/Pune-User-Group-2023294 # PuneDevCon 23

23. Get connected… http://www.puneusergroup.org http://www.facebook.com/puneusergroup http://twitter.com/puneusergroup http://www.linkedin.com/groups/Pune-User-Group-2023294 # PuneDevCon 24

24. Celebrating 14 glorious years of sharing passion 25 PUG Technology Foundation