**Phase 1** of the tutorial, named **Setup and Basic Simulation**, will cover tasks and skills such:
## Phase 1: Setup and Basic Simulation
This phase will cover essential tasks and skills such as:
* Downloading Unity Editor and the Perception package
* Fundamental interactions with Unity Editor (importing sample assets into your Unity project, working with prefabs and scenes, adding components to objects and prefabs, etc.)
* Learning about essential components of the Perception package and creating a basic simulation with these essential elements.
In order to get the best out of most perception-oriented machine learning models, the training data needs to contain a large-degree of variation. As a general rule of thumb, the more varied data you can feed to a model while training, the better it performs. This is achieved through randomizing various aspects of your simulation between frames. While you will use basic randomizations in Phase 1.
**Phase 2** of the tutorial will help you learn how to randomize your simulations in more complex ways by guiding you through writing your first customized randomizer in C#. This phase is called **Custom and Complex Randomizations**, and once you complete it, you will know how to:
## Phase 2: Custom and Complex Randomizations
In order to get the best out of most perception-oriented machine learning models, the training data needs to contain a large-degree of variation. As a general rule of thumb, the more varied data you can feed to a model while training, the better it performs. This is achieved through randomizing various aspects of your simulation between frames. While you will use basic randomizations in Phase 1, **Phase 2** of the tutorial will help you learn how to randomize your simulations in more complex ways by guiding you through writing your first customized randomizer in C#. This phase is called **Custom and Complex Randomizations**, and once you complete it, you will know how to:
Finaly, in **Phase 3**, which is simply named **Cloud**, you will learn how to:
* Generate larger-scale synthetic datasets by leveraging the power of Unity Simulation.
## Phase 3: Cloud
You will generally require a large amount of data to train your intended model. Generating data in these practical sizes will take incredible amounts of time to finish if performed on typical workstation computers. This is where the cloud comes in. In this phase, you will learn how to:
* Generate large-scale synthetic datasets containing hundreds of thousands of frames by leveraging the power of **Unity Simulation**.
* Generate common and custom statistics and visualizations for your cloud-generated data.
* Generate both common and custom statistics and visualizations for your cloud-generated data.
GitHub