The Bleeding Edge: Great Machine Learning Experiences In Your App With Cloud Functions & Firebase

Transcript

1. GREAT MACHINE LEARNING EXPERIENCES IN YOUR APP WITH CLOUD FUNCTIONS & FIREBASE PROSPER OTEMUYIWA - @unicodeveloper
2. THE BLEEDING EDGE
3. Speaker Bio Google I/O Extended 2017 3 ❖ Software Developer ❖ Consultant at Auth0 ❖ Open Sourcerer ❖ Self-Acclaimed Developer Evangelist ❖ Community Builder ❖ Jollof Rice Ambassador ❖ Google Developer Expert ❖ Sublime Text Advocate @unicodeveloper
4. The floor is Live Demo during Presentations Ire Aderinokun : @ireaderinokun
5. What is Machine Learning? Google I/O Extended 2017 z 5 Machine learning is a type of artificial intelligence (AI) that provides computers with the ability to learn without being explicitly programmed.
6. Machine learning focuses on the development of computer programs that can change when exposed to new data.
8. Machine learning focuses on the development of computer programs that can change when exposed to new data.
9. Machine Learning Experiences Google I/O Extended 2017 9 Self Driving Cars
10. Machine Learning Experiences Google I/O Extended 2017 10 Closed Captioning on Youtube
11. Machine Learning Experiences Google I/O Extended 2017 11 Gmail Smart Reply
12. Machine Learning Experiences Google I/O Extended 2017 12 Google Photos Image Search
13. Machine Learning Experiences Google I/O Extended 2017 13 Google Photos Image Search
14. Thou Developer, Now how do you implement this in your app?
15. Machine Learning Experiences - Cloud Vision API Google I/O Extended 2017 15 Automatically detect objects in images
16. Machine Learning Experiences - Cloud Vision API Google I/O Extended 2017e 16
17. Machine Learning Experiences - Cloud Vision API Google I/O Extended 2017 17
18. Machine Learning Experiences - Cloud Vision API Google I/O Extended 2017 1 8
19. Machine Learning Experiences - Cloud Vision API Google I/O Extended 2017 19
20. Machine Learning Experiences - Cloud Vision API Google I/O Extended 2017 20
21. cloud.google.com/vision
22. Machine Learning Experiences - Cloud Speech API Google I/O Extended 2017 22
23. Machine Learning Experiences - Cloud Speech API Google I/O Extended 2017 23 Google Cloud Speech API enables developers to convert audio to text by applying powerful neural network models in an easy to use API. The API recognizes over 80 languages and variants, to support your global user base
24. https://cloud.google.com/spee ch/
25. Machine Learning Experiences - Cloud Translation API Google I/O Extended 2017 25
26. Machine Learning Experiences - Cloud Translation API Google I/O Extended 2017 26 Cloud Translation API provides a simple programmatic interface for translating an arbitrary string into any supported language using state-of-the-art Neural Machine Translation.
27. https://cloud.google.com/tran slate/
30. Cloud Functions For Firebase Google I/O Extended 2017 30 Write Custom Server Code on Google Servers In response to events happening in your apps.
31. Google Cloud Functions are written in JavaScript, and execute in a Node.js runtime.
32. Triggers are at the Core
33. Triggers
34. Cloud Functions For Firebase Google I/O Extended 2017 34 What Triggers Are Available? ❖ Realtime Database Triggers ❖ Firebase Authentication Triggers ❖ Google Analytics for Firebase Triggers ❖ Cloud Storage Triggers ❖ Cloud Pub/Sub Triggers ❖ HTTP Triggers
35. Practical Use Cases Of Cloud Functions Google I/O Extended 2017 35 https://saythat.io
36. Practical Use Cases Of Cloud Functions Google I/O Extended 2017 36
37. Practical Use Cases Of Cloud Functions Google I/O Extended 2017 37
38. Practical Use Cases Of Cloud Functions Google I/O Extended 2017 38
39. https://github.com/laurenzlo ng/say-that Source Code
40. Practical Use Cases Of Cloud Functions Google I/O Extended 2017 40 Content Moderation ❖ Text Moderation
41. Practical Use Cases Of Cloud Functions Google I/O Extended 2017 41
42. Practical Use Cases Of Cloud Functions Google I/O Extended 2017 42 http://bit.ly/2scqovV
43. Practical Use Cases Of Cloud Functions Google I/O Extended 2017 43 Content Moderation ❖ Image Moderation ❖ By nature, needs to be performed in a trusted environment.
44. Practical Use Cases Of Cloud Functions Google I/O Extended 2017 44 Content Moderation - Image ❖ Image Moderation ❖ By nature, needs to be performed in a trusted environment.
45. #AmberRoseChallenge
47. You can actually avoid that in your apps. ML & Cloud Functions to the Rescue #BeWiseSon #BeWiseWoman
48. Practical Use Cases Of Cloud Functions Google I/O Extended 2017 48 exports.blurOffensiveImages = functions.storage.object().onChange(event => { const object = event.data; const file = gcs.bucket(object.bucket).file(object.name); // Exit if this is a move or deletion event. if (object.resourceState === 'not_exists') { return console.log('This is a deletion event.'); } // Check the image content using the Cloud Vision API. return vision.detectSafeSearch(file).then(data => { const safeSearch = data[0]; console.log('SafeSearch results on image', safeSearch); if (safeSearch.adult || safeSearch.violence) { return blurImage(object.name, object.bucket, object.metadata); } }); });
49. Practical Use Cases Of Cloud Functions Google I/O Extended 2017 49 To blur the image stored in Cloud Storage, we'll first download it locally on the Cloud Functions instance, blur the image with ImageMagick, which is installed by default on all instances, then re-upload the image to Cloud Storage:
51. I AM EXCITED, HOW DO I LEARN?
52. Learning Resources for Cloud Functions & Firebase Google I/O Extended 2017 52 Cloud Functions Docs - http://bit.ly/2qiq3F9
53. Collection of Sample Apps for Cloud Functions? The CakePHP 2017 Conference 53 ❖ Email Confirmation ❖ Delete unused Accounts ❖ Github to Slack ❖ Thumbnail Generation ❖ User data cleanup ❖ Extract Image Metadata Github Functions Samples - http://bit.ly/2sDT56x
54. Thank you #iO17Extended - @unicodeveloper