Deep Learning for Computer Vision

This repository contains six assigmnets of the course EECS 498-007 / 598-005 – Fall 2020. The link for the course is below.

link: EECS 498-007 / 598-005 – Fall 2020 <– Click here

Each assignment has a .py complimentary file that contains code that we use and reuse. The .ipynb files perform general setup of the development environment. Open first the .ipynb first and side by side the corresponding .py file

---

All recording for this course are public and can be found on this link -> Lecture Recordings

Assignment - 1

• Introduction to fundamental concepts of Pytorch
• Understand the basic Image Classification pipeline
  • the data-driven approach (train/predict stages)
• Understand the train/val/test splits
  • the use of validation data for hyperparameter tuning
• Implement and apply a k-Nearest Neighbor (kNN) classifier

Lectures to read for this assignment

• Lecture 2 – Image Classification – PDF

Assignment – 2

• Implement and apply a Multiclass Support Vector Machine (SVM) classifier
• Implement and apply a Softmax classifier
• Implement and apply a Two-layer Neural Network classifier
• Understand the differences and tradeoffs between these classifiers
• Practice implementing vectorized gradient code
  • checking against naive implementations
  • using numeric gradient checking

Lectures to read for this assignment

• Lecture 3 – Linear Classifiers – PDF
• Lecture 4 – Regularization + Optimization – PDF
• Lecture 5 – Neural Networks – PDF
• Lecture 6 – Backpropogation – PDF