This project was conducted for the AWS Udacity Machine Learning Engineer Nanodegree. If you copy too much from this project you could be chased for plagiarism.
Udacity does not have any public course review, so I would like to express that I do not recommend attending this particular Udacity course. I paid for it so I had to finish it, but both AWS and ML part of the course was bad. The course starter and example files had multiple bugs (typos, outdated API, missing lines of code). The AWS part of the course is already outdated. Course was released 11.2021, now it is 05.2022 and AWS UI already evolved in some parts making course tutorials unusable. The Udacity team is also struggling to provide support for students. I had some AWS access issue which wasn't solved for over a month - I had to complete it using personal account and additional budget. For the ML part, the course provide just bullet points, without any thorough explanation - you should be familiar with ML concepts in order to start this course.
Distribution centers often use robots to move objects as a part of their operations. Objects are carried in bins which can contain multiple objects. In this project, you will have to build a model that can count the number of objects in each bin. A system like this can be used to track inventory and make sure that delivery consignments have the correct number of items.
To build this project you will use AWS SageMaker and good machine learning engineering practices to fetch data from a database, preprocess it, and then train a machine learning model. This project will serve as a demonstration of end-to-end machine learning engineering skills that you have learned as a part of this nanodegree.
This project is based on the Udatity starter files avaiable here.
In the git repository there are two main directories:
- project_report -- contain Latex document with the project's report file
- project_proposal -- contain Latex document with the proposal file describing project overview
- project -- actual project code which can be executed on AWS or standalone to reach the project's goals.
This readme describe just general background for the project.
For the project files description please refer to README.md
file in the project/
directory.