Welcome to the

Deep Learning

for

Computer Vision

Course

Offered by Opencampus.sh

Opencampus.sh

EDU @ Opencampus.sh

The Machine Learning Program

WHO AM I?

I am: Luca
I studied: Engineering and Computer Vision
Favourite song or artist: Blowing in the Wind by Bob Dylan

WHO ARE YOU

You are: name is enough, whatever else is welcome - if you can help with the pronunciation, I would be grateful
You studied: a bit about your learning background, knowledge or experience
Favourite song or artist: what's yours and why or how did it happen?

Overview

  • General Introduction - 25.10
  • Foundations of Convolutional Neural Networks - 01.11
  • First Convolutional Model Application - 08.11
  • Classic CNN Architectures - 15.11
  • Transfer Learning with CNNs - 22.11
  • Detection Algorithms - 29.11
  • Project Checkpoint | Image Segmentation - 06.12
  • Face Recognition - 13.12
  • Art Generation with Neural Style Transfer - 20.12
  • Bonus CNN - 10.01
  • Presentation of Final Projects - 17.01

Projects - Basics

Less homework, more projects

Projects are not graded

Projects are made in groups

Project Structure

Projects start right away

There will be a Project Checkpoint on the 06 of December

To complete the project, we ask you to create:

  • A public repository
  • A notebook with working code and explanation/comments
  • A small video/screen recording (or we record your presentation.)

Projects Template

Projects Page

Project Ideas

I have three suggestions for you:

  1. Regional research project with real world application
  2. AI + Robotic: learn to connect software and hardware
  3. AI WebApp: make the project available for everyone

Otherwise check out the projects from last semester for some inspirations:
projects page

Protect Planet Bee

Protect Planet Bee

The aim of the project is to study if and how feeding bees with a special type of mushrooms is beneficial for the animals.

In order to prove this, they need to count the number of bees.

Impossible to do it by hand, they look for an AI-powered solution, that automatically counts the bees from the picture

Jetbot

AI-powered robot

A small moving robot with a camera and a GPU-capable processor

Obstacle detection

WebApp

Create a web app that everyone can use by adjusting your code

Streamlit

Gradio

Tools used in the Course

Zoom Sessions

Every Monday at 18.00

1 - Quiz: we start with an ungraded quiz about the last week

2 - Discussion: we discuss shortly about the questions and clarify if anyone has doubts

3 - Questions: we start an open discussion, all together or in smaller group depending on how many people join

4 - Exercises: we go through the assignment together and comment the code

Remember: there are no grades, we are in a safe space open to discussions, most of the time there is no right or wrong answer.

Weekly Material

This semester we have only 4 coursera weeks

Only one coursera assignment per week (8 assignemnts = 8 weeks)

Coursera videos can be distributed, but usually each 2 weeks.

Additional videos/material on each second weeks.

For the next week

  • Finish the first homework and check first week's video of the CNN course