Onboarding

Welcome to the Onboarding of KITcar Machine Learning! Here, you can dive into our repository. You will be introduced to the fundamental structure of the repository. There are also several tasks you need to complete!

We write our code in Python3.8. If you haven’t used Python before, you can take a look at one of the many Python courses available online. Here are just a few suggestions:

• https://docs.python.org/3/tutorial/index.html

• https://www.youtube.com/watch?v=YYXdXT2l-Gg&list=PL-osiE80TeTt2d9bfVyTiXJA-UTHn6WwU

For our neural networks we use PyTorch. Here are a few suggestions, to get used with PyTorch:

• https://pytorch.org/tutorials/beginner/basics/intro.html

• https://youtube.com/playlist?list=PLqnslRFeH2UrcDBWF5mfPGpqQDSta6VK4

Setup

Before we get started, you need to install kitcar-machine-learning by following the Installation. Also make sure that you have correctly setup DVC .

Overview

During the onboarding you will go through multiple smaller tutorials in which you will learn to add and use datasets, program and train a small neural network. We use the MNIST dataset as an example. Throughout the onboarding, you are encouraged to not only complete the tasks, but also try to understand what we are doing and why the tools and processes are useful.

Content

• 1. Repository
  • 1.1. Root
  • 1.2. Docs
  • 1.3. Init
  • 1.4. Machine Learning
• 2. Datasets
  • 2.1. Prepare the Data
  • 2.2. Explore the data
  • 2.3. Adding Datasets
• 3. Defining Neural Networks
  • 3.1. Model
  • 3.2. Testing
  • 3.3. Training
  • 3.4. Improvements
• 4. DVC