Project: Custom Prediction Routine on Google AI Platform

Start Date: 03/01/2020

Course Type: Common Course

Course Link:

Explore 1600+ online courses from top universities. Join Coursera today to learn data science, programming, business strategy, and more.

About Course

In this 2-hour long project-based course, you will learn how to deploy, and use a model on Google’s AI Platform. Normally, any model trained with the TensorFlow framework is quite easy to deploy, and you can simply upload a Saved Model on Google Storage, and create an AI Platform model with it. But, in practice, we may not always use TensorFlow. Fortunately, the AI Platform allows for custom prediction routines as well and that’s what we are going to focus on. Instead of converting a Keras model to a TensorFlow Saved Model, we will use the h5 file as is. Additionally, since we will be working with image data, we will use this opportunity to look at encoding and decoding of byte data into string for data transmission and then encoding of the received data in our custom prediction routine on the AI Platform before using it with our model. This course runs on Coursera's hands-on project platform called Rhyme. On Rhyme, you do projects in a hands-on manner in your browser. You will get instant access to pre-configured cloud desktops containing all of the software and data you need for the project. Everything is already set up directly in your Internet browser so you can just focus on learning. For this project, you’ll get instant access to a cloud desktop with (e.g. Python, Jupyter, and Tensorflow) pre-installed. Prerequisites: In order to be successful in this project, you should be familiar with Python programming, Google Cloud Platform. Notes: - You will be able to access the cloud desktop 5 times. However, you will be able to access instructions videos as many times as you want. - This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.

Course Syllabus

Custom Prediction Routine on Google AI Platform

Deep Learning Specialization on Coursera

Course Introduction

In this 2-hour long project-based course, you will learn how to deploy, and use a

Course Tag

Related Wiki Topic

Article Example
Google Custom Search The Google Custom Search platform consists of three services:
Google Art Project The resulting Google Art Project platform is a Java-based Google App Engine Web application, which exists on Google’s infrastructure.
Google Custom Search Google Custom Search (formerly known as Google Co-op) is a platform provided by Google that allows web developers to feature specialized information in web searches, refine and categorize queries and create customized search engines, based on Google Search. The service allows users to narrow the 11.5 billion indexed webpages down to a topical group of pages relevant to the creator's needs. Google launched the service on October 23, 2006
Google Art Project Google Arts & Culture (formerly Google Art Project) is an online platform through which the public can access high-resolution images of artworks housed in the initiative’s partner museums. The project was launched on 1 February 2011 by Google, in cooperation with 17 international museums, including the Tate Gallery, London; the Metropolitan Museum of Art, New York City; and the Uffizi, Florence.
Google Cloud Platform Google Cloud Platform is a part of a suite of enterprise services from Google Cloud and provides a set of modular cloud-based services with a host of development tools. For example, hosting and computing, cloud storage, data storage, translations APIs and prediction APIs.
Google Art Project The Google Art Project stirred up debate among scholars, museum personnel, art critics, and news writers. Since its initial launch, the Google Art Project has received fairly consistent positive feedback, and a variety of criticisms. With the second generation platform, Google appears to have responded to some earlier criticisms.
Google Cloud Platform Google Cloud Platform is a cloud computing service by Google that offers hosting on the same supporting infrastructure that Google uses internally for end-user products like Google Search and YouTube. Cloud Platform provides developer products to build a range of programs from simple websites to complex applications.
Google Art Project On April 3, 2012, Google announced the expansion of the Art Project to include 151 museums. At the time of the announcement, 46 of those museums and their works are available on the website. Like the original 17 partners, each of the new partners has a gigapixel image of one of their works on the Art Project platform.
Google Custom Search Released on October 23, 2006, Google Custom Search allows anyone to create their own search engine by themselves. Search engines can be created to search for information on particular topics chosen by the creator. Google Custom Search Engine allows creators to select what websites will be used to search for information which helps to eliminate any unwanted websites or information. Creators can also attach their custom search engine to any blog or webpage. Google AdSense results can also be triggered from certain search queries, which would generate revenue for the site owner.
Google Art Project After this controversy, Google took a different approach on intellectual property rights for the Google Art Project. The Art Project's intellectual property policy is:
Google Art Project On April 3, 2012, Google announced a major expansion to the Art Project as it signed partnership agreements with 151 museums from 40 countries. The platform now features more than 32,000 artworks from 46 museums, and the image acquisition process is underway at the remaining partner museums. This expansion includes works from institutions like the Art Gallery of Ontario, the White House, the Australian Rock Art Gallery at Griffith University, the Museum of Islamic Art, Doha, and the Hong Kong Museum of Art. Additionally, Google launched a second, improved version of the website with new Google+ features, enhanced search capabilities, and a series of educational tools. Google intended for this second-generation platform to be a global resource; accordingly, the Art Project is now available in 18 languages, including English, Japanese, Indonesian, French, Italian, Polish, and Portuguese.
Google Art Project Many scholars have argued that we are experiencing a breakdown of the canon of high art, and the Google Art Project is beginning to reflect this. When it just included the Grand Masters of Western Art, the Google Art Project faced strong criticism. As a result of this outburst, the website now includes some indigenous and graffiti artworks. This platform also provides a new context through which people encounter art, ultimately reflecting this shift away from the canon of high art.
Google Art Project As New York Times art reviewer Roberta Smith said: “[Google Art Project] is very much a work in progress, full of bugs and information gaps, and sometimes blurry, careering virtual tours.” Though the second generation platform solved some technological issues, Google plans to continue developing additional enhancements for the site. Future improvements currently under consideration include: upgrading panorama cameras, more detailed web metrics, and improved searchability through metatagging and user-generated metatagging. Google is also considering the addition of an experimental page to the platform, to highlight emerging technologies that artists are using to showcase their works.
Prediction market Around 1990 at Project Xanadu, Robin Hanson used the first known corporate prediction market. Employees used it in order to bet on, for example, the cold fusion controversy.
Project Zero (Google) Project Zero is the name of a team of security analysts employed by Google tasked with finding zero-day vulnerabilities. It was announced on 15 July 2014.
Google Hangouts On February 16, 2015, Google announced it would be discontinuing Google Talk and instructed users to migrate to the Hangouts app on the Chrome browser platform.
Google Art Project The Art Project emerged as a result of Google’s “20-percent time” policy, by which employees are encouraged to spend 20% of their time working on an innovative project of interest. A small team of employees created the concept for the Art Project after a discussion on how to use Google technology to make museums’ artwork more accessible. The Art Project concept fits Google's mission "to organize the world’s information and make it universally accessible and useful." Accordingly, in mid-2009, Google executives agreed to support the project, and they engaged online curators of numerous museums to commit to the initiative.
Google Art Project To move from concept to reality, the Google team leveraged existing technologies, including Google Street View and Picasa, and built new tools specifically for the Art Project.
Google Art Project The Art Project has been integrated with Google's social media platform (Google+) to enable users to share their personal collections with their networks. This integration also lets site visitors use Google+ Hangouts for more interactive purposes. These situations might include: a professor giving an online lecture to students, engaging in video and shared-screen discussions about a collection, or an expert leading a virtual tour of a distant museum to remote attendees.
Prediction Nowadays sport betting is a huge business; there are many websites (systems) alongside betting sites, which give tips or predictions for future games. Some of these prediction websites (tipsters) are based on human predictions, but others on computer software sometimes called prediction robots or bots. Prediction bots can use different amount of data and algorithms and because of that their accuracy may vary.