Techniques to generate training data
•Download as PPTX, PDF•
0 likes•154 views
How to generate more training data without taking more photos for image classification.
Recommended
Recommended
More Related Content
Recently uploaded
Recently uploaded (20)
Featured
Featured (20)
Techniques to generate training data
- 1. Hot Dog Not Hot Dog!
- 2. Generate new training data Without taking more photos Annie Flippo October, 2017 Southern California Data Science Conference Hot Dog, Not Hot Dog!
- 8. The Tech is good Just needs more training data Image Source: HBO
- 11. I work as a Manager of Analytics At Thinknear by Telenav
- 12. We are a location-based advertising platform
- 13. GPS navigation for vehicles and mobile phones
- 14. Cat Dog Mug Hat
- 18. Real-life Data
- 19. Real-life Data
- 20. Real-life Data
- 21. Real-life Data
- 22. Hot Dogs or Meatballs? Image recognition is one of the most important developments in AI. Close your eyes and imagine: - Taking a shower - Eating your lunch - Driving
- 28. Our Eyes Only
- 29. Autonomous Driving: Sign Recognition
- 30. Real Signs
- 31. Real Signs
- 32. Real Signs
- 33. Why is object recognition so hard? Image Source: Stanford University, cs231n.github.io/classification
- 34. The Humble Stop Sign
- 35. The Humble Stop Sign
- 36. Be Aware of Image Hacking 1 Image Source: https://codewords.recurse.com/issues/five/why-do-neural-networks-think-a-panda-is-a-vulture
- 37. Be Aware of Image Hacking 2 Image Source: https://codewords.recurse.com/issues/five/why-do-neural-networks-think-a-panda-is-a-vulture
- 38. Be Aware of Image Hacking 3 Image Source: https://medium.com/@ageitgey/machine-learning-is-fun-part-8-how-to-intentionally-trick-neural-networks-b55da32b7196
- 39. Be Aware of Image Hacking - Fake Fakes This could be a devastating example if the autonomous vehicle is trained to drive over newspaper! Pedestrian (98.5%) Newspaper (95.9%)
- 40. What can we do? I need better training! Any ideas?
- 41. Generate Training Data Idea 1 Augment source image by: Rotation Perspective Transformation
- 42. Generate Training Data Idea 2 Blurring Brightness Adjustment
- 43. Generate Training Data Idea 3 Add NoiseShearing
- 44. Apply Blurring
- 45. Apply Noise
- 47. Apply Rotations
- 48. All Adjustments
- 49. Dropout in Neural Network
- 50. Time Saving Tip Generate many variations per source image but: ● Don’t save to disk (slow and takes space) ● Run it under a Python Generator Object ○ Generate images as you train (fast and scalable)
- 51. Train a Winning Model … and become a billionaire! Image Source: HBO
- 52. Thank You acflippo @acflippo Slides and code: bit.ly/scds-acflippo
Editor's Notes
- A cast of 30 something techies continuously try to get funding for their ideas. They go to tech competitions, conferences but were always circumvented by their competitor, nemesis and billionaire CEO, Gavin Belson.silicon valley opening scene season 1
- A cast of 30 something techies continuously try to get funding for their ideas. They go to tech competitions, conferences but were always circumvented by their competitor, nemesis and billionaire CEO, Gavin Belson.silicon valley opening scene season 1
- A cast of 30 something techies continuously try to get funding for their ideas. They go to tech competitions, conferences but were always circumvented by their competitor, nemesis and billionaire CEO, Gavin Belson.silicon valley opening scene season 1
- Erlich, the serial entrepreneur, runs an incubator from his house including this group of startup guys. One of them is Jing Yang, the freeloader of the group.
- Finally, Erlich through some miscommunication sold Jing Yang’s idea for a food identification app. During the demo, the app only identifies hot dogs and all other foods as not hot dogs.
- Perplexed to the success of the app. Dinesh wonders ...
- Erlich had the idea to use the student from his friend’s stanford class to scrape the internet for food pictures to train Jing Yang’s model. But the students steal his idea, rendering his company worthless. Erlich again had his butt handed to him because he doesn’t have enough understanding how to train a neural network.
- Erlich had the idea to use the student from his friend’s stanford class to scrape the internet for food pictures to train Jing Yang’s model. But the students steal his idea, rendering his company worthless. Erlich again had his butt handed to him because he doesn’t have enough understanding how to train a neural network.
- See these perfect specimens of hot dog pictures taken probably by a professional food photographer. For any neural network, training data is very important. See on a simple task of identifying a hot dog. How one simple hot dog can be represented?
- See these perfect specimens of hot dog pictures taken probably by a professional food photographer. For any neural network, training data is very important. See on a simple task of identifying a hot dog. How one simple hot dog can be represented?
- For most activities, us, humans only need to use our eyes - to drive, to eat, to catch a ball. We haven’t needed radars, lidars, other electronic sensors.
- I’ll show you some signs and you all recognize these. They’re shown under perfect conditions.
- Life is not like that. Even for just the School Zone Sign. There are lots of them. Some are very localized to the region. Please use shotguns only because a handgun would just be too dangerous!
- Life is not like that. Even for just the School Zone Sign. There are lots of them. Some are very localized to the region. Please use shotguns only because a handgun would just be too dangerous!
- Life is not like that. Even for just the School Zone Sign. There are lots of them. Some are very localized to the region. Please use shotguns only because a handgun would just be too dangerous!
- Another way to get a robust classification neural net model is to use Dropout. It sounds kind of crazy and un-intuitive. Why would you want to wipe out information in the middle of training your network? Because you don’t want to model to count on any specific features because at anytime that feature may not be there.
- Go forth, generate a gazillion training images for your winning model and become a billionaire!
- Go forth, generate a gazillion training images for your winning model and become a billionaire!