AI4ALL-Course-Project-Image-Segmentation

This repository contains a light version of sacmehta's EdgeNets and a few exercises for students in the AI4ALL program to navigate. Please check out https://github.com/sacmehta/EdgeNets for the full model

Goals:

• Understand how to navigate a research project
• Understand how to use the shell for basic commands
• Understand how image segmentation works on a high level
• Understand how to test a machine learning model
• Understand how to evaluate a machine learning model

Steps:

Starting off

1. To start with, go through this project and look at a couple of files. Try to see how they are related to each other. We will go over this together just to make sure everyone understands.
2. Clone this repository from Github using the following command: git clone https://github.com/rithvik-doshi/AI4ALL-Course-Project-Image-Segmentation (if git is not installed on your machine, download a zip file of the project to your machine)

# using python:
import os
os.system("git clone https://github.com/rithvik-doshi/AI4ALL-Course-Project-Image-Segmentation.git")

3. Take a look at and read the intro to shell file, so that you can learn how to use the command line
4. Look around in some of the other project files and folders.

Investigating the project files

1. Take a look at the main.py file. This is the python file that is intended to be run to make the whole project work.
2. Trace the imports of the file and see if you can find any related .py files. What do they do on a large scale?
3. Which file is the machine learning model found in?
4. Which file does the data collection occur in?
5. Which file does the data visualization occur in?

Filling in the blanks

1. Read test_segmentation.py, data.py and main.py in that order. Try to understand the flow of the code and how things are taking place in the files.
2. Make sure to test each part out to make sure it is working before moving on to the next file, wherever applicable.
3. Fill in the blanks in main.py and take notes about the key concepts that you learn

Final Presentation

1. Create a presentation with your group covering the following topics:

• Briefly and broadly describe the machine learning model at work
• What task is the ML model undertaking?
• How does the project test the model?
• How was the data about the model collected?
• How did you go about creating the visualization of the data?
• What were some other things you learned about working on a ML project?