Quick Start Into TensorFlow - GDG Festac-Ojo I/O 2019 Extended

Quick Start Into TensorFlow - GDG Festac-Ojo I/O 2019 Extended

Transcript

1. Getting Started With TensorFlow +OlayinkaPeterOluwafemi @olayinkapeter_
2. What is TensorFlow? TensorFlow is an open source library for numerical computation and large-scale machine learning.
3. You must have come across words like: • Artificial intelligence • Machine learning • Neural network • Deep learning
4. Artificial Intelligence: A field of computer science that aims to make computers achieve human-style intelligence. There are many approaches to reaching this goal, including machine learning and deep learning.
5. • Machine Learning: A set of related techniques in which computers are trained to perform a particular task rather than by explicitly programming them.
6. • Neural Network: A construct in Machine Learning inspired by the network of neurons (nerve cells) in the biological brain. Neural networks are a fundamental part of deep learning.
7. • Deep Learning: A subfield of machine learning that uses multi-layered neural networks. Often, “machine learning” and “deep learning” are used interchangeably.
8. Machine learning on Google Cloud Platform
9. Generic task Custom task Stuff someone has solved before Very specific to your dataset “puppy” “Sylvester” Input to prediction
10. Generic task Custom task Stuff someone has solved before Very specific to your dataset Pre-trained models (Machine Learning APIs) Cloud Machine Learning Engine Application developers Data scientists and ML practitioners
11. Sometime in late 2017, I published Toodoo, a Firebase-powered app that basically lets you add tasks you want to be reminded of, but with some Machine Learning capabilities.
12. Toodoo is not special. Except that it solves the problem of: Users spending large amount of time and/or having trouble in trying to read small printed material in a voluminous page
13. Hence, allowing users to: • Hunt for text material (in languages such as Chinese, English, Finnish, French, German, Japanese, Korean, Portuguese & Spanish) with a device camera to capture an image. • Process the image and extract the text from it using powerful Google Cloud vision Optical Character Recognition (OCR) support. • Copy the extracted image to clipboard, and add them as to-dos
16. The need for custom data
17. Identify your own puppy among hundreds of puppies “Sylvester” “Driver” here could be referred to as ‘taxi driver’, for example Importance of specific prediction or translation
18. • Cloud ML Engine allows you to build, train, and serve custom models with your own data
19. TensorFlow is an end-to-end open source platform for machine learning. It has a comprehensive, flexible ecosystem of tools, libraries and community resources that lets researchers push the state-of-the-art in ML and developers easily build and deploy ML powered applications.
20. bit.ly/tensorflow-starter-lab
21. @olayinkapeter_