Tensorflow Estimator

This talk covers Tensorflow estimator and implement it on Google ML engine. This talk was delivered first at GDG Ahmedabad.

Transcript

1. by Pratik Parmar aka Pintudo Machine Learning
2. I AM Pratik Parmar Hello! And I am here to bore you with Machine Learning.
3. Machine Learning for everyone
4. “ Machine Learning is using many examples to answer questions
7. ? Machine learning is awesome, except when it forces you to do advanced math. Isn’t it?
8. Tensorflow Estimators
9. Tensorflow Estimator
10. App Idea: Food Search engine 0 And foodies be like...
11. Version 2.0 Memorize all the things
12. Version 3.0 More generalized recommendations for all
13. No good deeds goes unpunished
14. Wide and Deep Memorization Relevance Generalization Diversity
15. Wide and Deep model
16. After evaluation The workflow for building machine learning models often ends at the evaluation stage: you have achieved an acceptable accuracy, and “ta-da! Mission Accomplished.”
17. Why ??? Maybe, going the extra mile to put your model into production is not always needed. And even when it is, this task is delegated to a system administrator.
18. “ During my course at Coursera I was always asking myself — I have my model, which I can run in Jupyter Notebook and see the result, but what can I do with it? How can other use it?
19. How to deploy Machine Learning models?
20. Give some space because
21. NO QUESTIONS PLEASE
22. Thank you for bearing me