YGLF_2019.pdf

Transcript

1. The Future of Machine Learning & JavaScript @jawache YGLF 2019
2. Asim Hussain @jawache codecraft.tv microsoft.com
3. https://aka.ms/jawache-cda @jawache
4. @jawache https://www.palinternship.com/
5. @jawache
6. Asim Web Development Machine Learning This is @EleanorHaproff's slide
8. @jawache
9. TheMojifier™ @jawache
11. @jawache themojifier.com
13. How to Calculate Emotion? @jawache
14. (1) Detect Facial Features @jawache
15. https://towardsdatascience.com/facial-keypoints-detection-deep-learning-737547f73515
16. (2) Use a Neural Network @jawache
17. Neural Networks Axon Dendrites Axons Body @jawache
18. 1 23 8.6 -0.5 2.1 Activation Function @jawache Neural Networks
19. 1 23 8.6 -0.5 2.1 x x activation(...) = -11.5 = 18.06 7.01 !-> !-> } @jawache Neural Networks
20. Output 0 0 1 Input @jawache Neural Networks
21. 1.1 4.2 0.3 4 12 93 3 @jawache Neural Networks
22. 1.1 4.2 0.3 4 12 93 @jawache 8 - 8 = -5 3 Neural Networks
23. 1.1 4.2 0.3 4 12 93 @jawache - 8 = -5 3 8 Neural Networks
24. 0.1 9.2 0.2 4 12 93 @jawache 8 8 Neural Networks
25. @jawache https://azure.microsoft.com/services/cognitive-services/face/
26. https:!//<region>.api.cognitive.microsoft.com/face/v1.0/detect { "url": "<path-to-image>" } @jawache
27. @jawache
28. Summary @jawache
29. • Neural Networks are incredibly powerful • Conceptually, they are simple to understand @jawache Summary
30. TensorFlow, MobileNet & I'm fine @jawache
31. @jawache
32. @jawache
33. @jawache
34. TensorFlow.js @jawache
35. TensorFlow.js Train models Load pre-trained models @jawache
36. https://github.com/tensorflow/tfjs-models @jawache MobileNet
37. https://azure.microsoft.com/services/cognitive-services/computer-vision/ @jawache
38. https://codepen.io/sdras/full/jawPGa/ @jawache
39. @jawache https://twitter.com/ollee/status/930303340516216832
40. @jawache https://twitter.com/FrontendNE/status/930120267992616960
41. @jawache https://twitter.com/chrispiecom/status/930407801402347520
42. Summary @jawache
43. • TensorFlow.js doesn't have any dependancies • MobileNet is a simple way to analyse images • Azure Computer Vision API ❤ @jawache Summary
44. Image2Image @jawache
45. DEMO @jawache https://zaidalyafeai.github.io/pix2pix/cats.html
46. @jawache Generator Discriminator ✅ ❌
47. @jawache Generator Discriminator ✅ ❌
48. @jawache Generator Discriminator ✅ ✅
49. @jawache
50. @jawache
51. @jawache
52. @jawache https://github.com/NVIDIA/vid2vid
53. @jawache https://github.com/NVIDIA/vid2vid
54. @jawache https://github.com/NVIDIA/vid2vid
55. @jawache https://github.com/hanzhanggit/StackGAN
56. Summary @jawache
57. • GANs learn to generate new images • They take a lot of compute to train • But the generator model can be run in the browser @jawache Summary
58. @jawache aka.ms/mojifier
59. Asim Hussain @jawache codecraft.tv microsoft.com