Custom Vision Events

Microsoft Custom Vision Event Introduction

Our short welcome video will introduce you to the event and how to get started

What you need to do

The following short list of items summarises the next actions you need to take to start developing your game playing bot and to enter your bot into the event's tournament:

  1. Sign up for an account on the aigaming.com site.

  2. Create a Microsoft Azure account if you don't already have one.

  3. Create and train your own Custom Vision Image Recognition engine by following our explanatory video How To Train a Custom Vision Model

  4. Watch at least the next two videos below on this page

    1. How to use your Custom Vision model in your Python Code

You should now have everything you need to get started. Watch the other videos below for more specific information.

REMEMBER: The event culminates in a tournament. You must enter your code file into the tournament before it starts in order to be included (as explained in the video here).

Our Tip: Submit your code file in the tournament well in advance. You can still work on the code and change it after it has been submitted to the tournament, just make sure you are confident that the code runs without errors at the tournament start time.

More Information

There are more videos to show you how to compete in the event and how to modify the Template code.

How to train a Custom Vision model

In order to have access to the Microsoft Computer Vision services, you need to create an API key in your Azure account. The next video shows you how to create the key and add it the code templates on the AI Gaming site.

How to use the Microsoft Computer Vision API to identify the visual content in images.

Using the API is the first step to playing the Rummy Vision game. You will use it to find out what the image on each card in the game is, and then you can decide which cards to play to score points in the game. There is a complete code example of how to call the Microsoft Computer Vision API to analyse images on the AI Gaming site.

This video shows you how to use that code example, including what needs to be set up to call the API, how to make the call and how to interpret the response that the API sends back. This will give you a great step toward using the API in your code when you play the game.

Introduction to coding your game playing bot

Learn exactly where you need to add your code to develop your game playing bot. What information you will receive, and what information you need to return in order to play the game.

How to enter your code into a tournament

Entering your code into a tournament lets you find out how good your game playing bot is. Each event will have at least one tournament and the video below gives you a quick overview of how to make sure your code is registered to play.

Introduction to the editor and running games

The Online Code Editor is where you spend most of your time as you write the code for your automated game playing bot. It's also where you run the code to play the games. Find out all about the Online Code Editor and how to play games in this video

Video coming soon

Creating a Computer Vision API key and reviewing the API response

The Microsoft Cognitive Services Computer Vision Analyze API returns extensive information on the image that was analysed. This video shows how this information can be displayed within the Online Code Editor (OCE) and therefore the relevant components required to play the game can be extracted. Column three of the OCE is used to display the result returned and we explain how this can be interpreted into Python code in your solution to access the relevant parts of the data.

How to Navigate JSON Objects Using Python Dictionaries

JSON objects are widely used to transfer data to and from API services. They are human readable text strings which adhere to a formal syntax which means they are also readable in software. JSON objects can be easily manipulated in Python code by converting them to or from dictionary objects. This video introduces the format of JSON objects, demonstrates how to convert them to and from Python dictionary objects, and gives examples of how to work with dictionaries in your code.

Best steps to improve your code

We recommend tackling the following steps in order as the best approach to improving your code:

  1. Implement Landmark matching.

  2. Implement text recognition and word matching

  3. Read the tile backs to match tiles from the same category

  4. Check if you can match tiles in the bonus category

  5. Wait before matching any tiles to match tiles in consecutive Bonus Categories.

More information

For more detailed information about developing your solution for the Match Game, go to the Match Game specific help page here.

For our written Really Quick Start summary of how to starting coding solutions on the site go to our Really Quick Start page here.