What an ML-ful World! MLKit for Android dev.

Transcript

1. What an ML-ful world Britt Barak
2. Once upon a time @BrittBarak
3. beta @BrittBarak
4. ML Capability ?! @BrittBarak
5. Who is afraid of Machine Learning? & First Steps With ML-Kit @BrittBarak
6. Britt Barak Developer Experience, Nexmo Google Developer Expert Britt Barak @brittBarak
8. @BrittBarak
9. = @BrittBarak
10. § What’s the difference? @BrittBarak
11. …and classify? @BrittBarak
12. @BrittBarak
13. This is a strawberry @BrittBarak
14. This is a strawberry Red Seeds pattern Narrow top leaves @BrittBarak Pointy at the bottom Round at the top
15. Strawberry Not Not Not Strawberry Strawberry Not Not Not @BrittBarak
16. ~*~ images ~*~ @BrittBarak
17. @BrittBarak Vision library
18. Text Recognition @BrittBarak
19. Face Detection @BrittBarak
20. Barcode Scanning @BrittBarak
21. Image Labelling @BrittBarak
22. Landmark Recognition @BrittBarak
23. Custom Models @BrittBarak
24. Example @BrittBarak
25. @BrittBarak
26. @BrittBarak
27. Detector detector .execute(image) Result: @BrittBarak “Ben & Jerry’s pistachio ice cream”
28. 1. Setup Detector @BrittBarak
29. Local or cloud? @BrittBarak
30. @BrittBarak
31. Local •Realtime •Offline support •Security / Privacy •Bandwith •… @BrittBarak
32. Cloud •More accuracy & features •But more latency •Pricing @BrittBarak
33. 1. Setup Detector @BrittBarak
34. Text Detector textDetector = FirebaseVision.getInstance() @BrittBarak
35. Text Detector textDetector = FirebaseVision.getInstance() .onDeviceTextRecognizer @BrittBarak
36. Text Detector textDetector = FirebaseVision.getInstance() .cloudTextRecognizer @BrittBarak
37. 2. Process input @BrittBarak
38. FirebaseVisionImage •Bitmap •image Uri •Media Image •byteArray •byteBuffer @BrittBarak
39. image = FirebaseVisionImage.fromBitmap(bitmap) @BrittBarak Text Detector
40. 3. Execute the model @BrittBarak
41. Text Detector textDetector.processImage(image) @BrittBarak
42. Text Detector textDetector.processImage(image) .addOnSuccessListener { } @BrittBarak
43. Text Detector textDetector.processImage(image) .addOnSuccessListener { firebaseVisionTexts -> processOutput(fbVisionTexts) } @BrittBarak
44. 4. Process output @BrittBarak
45. firebaseVisionTexts.text @BrittBarak
46. someTextView.text = firebaseVisionTexts.text @BrittBarak UI
47. Result @BrittBarak
48. Result @BrittBarak
49. (another) Example : Labelling @BrittBarak
50. Detector detector .execute(image) Result: @BrittBarak ice cream pint
51. Vegetables Deserts Vegetables
52. 1. Setup Detector @BrittBarak
53. Image Classifier imageDetector = FirebaseVision.getInstance() @BrittBarak
54. Image Classifier imageDetector = FirebaseVision.getInstance() .visionLabelDetector @BrittBarak
55. Image Classifier imageDetector = FirebaseVision.getInstance .visionCloudLabelDetector @BrittBarak
56. 2. Process input @BrittBarak
57. image = FirebaseVisionImage.fromBitmap(bitmap) @BrittBarak Image Classifier
58. 3. Execute the model @BrittBarak
59. Image Classifier imageDetector.detectInImage(image) @BrittBarak
60. Image Classifier imageDetector.detectInImage(image) .addOnSuccessListener{ } @BrittBarak
61. Image Classifier imageDetector.detectInImage(image) .addOnSuccessListener{ fBLabels -> processOutput(fBLabels) } @BrittBarak
62. 4. Process output @BrittBarak
63. fbLabel.label fbLabel.confidence fbLabel.entityId @BrittBarak
64. UI for (fbLabel in labels) { s = "${fbLabel.label} : ${fbLabel.confidence}" } @BrittBarak
65. Result
66. Result
67. It is an ML-ful world Enjoy!
68. Thank you! Keep in touch!