TensorFlow is an open source software library for high performance numerical computation that's great for writing models that can train and run on platforms ranging from your laptop to a fleet of servers in the Cloud to an edge device. This quest takes you beyond the basics of using predefined models and teaches you how to build, train and deploy your own on Google Cloud.
Overview
Syllabus
- Learning TensorFlow: the Hello World of Machine Learning
- In this lab, you learn the basic 'Hello World' of machine learning. Instead of programming explicit rules in a language such as Java or C++, you build a system that is trained on data to infer the rules that determine a relationship between numbers.
- AI Platform: Qwik Start
- In this lab you train and deploy a TensorFlow model to AI Platform for serving (prediction). Watch these short videos Harness the Power of Machine Learning with AI Platform and AI Platform: Qwik Start - Qwiklabs Preview.
- Classify Images of Cats and Dogs using Transfer Learning
- In this lab, you will learn how to classify images of cats and dogs by using transfer learning from a pre-trained network.
- Running Distributed TensorFlow using Vertex AI
- In this lab, you will use TensorFlow's distribution strategies and the Vertex AI platform to train and deploy a custom TensorFlow image classification model to classify an image classification dataset.
- Creating an Object Detection Application Using TensorFlow
- This lab will show you how to install and run an object detection application. The application uses TensorFlow and other public API libraries to detect multiple objects in an uploaded image.
