Leonid Sigal

Associate Professor, University of British Columbia

 
 
 

Menu

Home | About | Biography | CV Students and Collaborators | Research | Teaching | CPSC 425
Winter 1, 2020
CPSC 425
Winter 2, 2019
CPSC 425
Winter 2, 2018
CPSC 532S
Winter 2, 2018
CPSC 425
Winter 1, 2018
CPSC 532L
Winter 2, 2017
CMU 15-869
Fall 2012
CMU 16-824
Spring 2012
CSCD18 Fall 2008 CSCD18 Fall 2007 Publications | Code and Data |

Contact

Dep. of Computer Science
University of British Columbia
ICCS 119
2366 Main Mall
Vancouver, B.C. V6T 1Z4
CANADA

Phone: 1-604-822-4368
Email: lsigal at cs.ubc.ca
 
 
 

Due: At the end of day11:59pm, Wednsday, December 2, 2020.

The purpose of this assignment is to introduce you to deep learning. Specifically, the assignment consists of three parts: In the first part, you will implement various PyTorch deep learning layers using Numpy; in part two, you will experiment with different hyper-parameters on a image classification task and find the best hyper-parameters; lastly, you will investigate a state-of-the-art neural architecture from the PyTorch model zoo.

The assignment

Since we will be experimenting with some cutting edge models, to avoid your need to install dependencies, we will be using Google Colab exclusively for this assignment.

Instructions to kick start the assignment:

  1. Download the assignment package hw6.zip
  2. Unzip hw6.zip.
  3. Open Google Colab here (https://colab.research.google.com)
  4. Click "Upload" and upload the file deep_learning.ipynb.
  5. Click on the "folder-like" icon on the left and click "Upload"
  6. Add the files (hw_utils.py, birb.jpg) to colab.

Deliverables

Hand in your Jupyter Notebook. You do not need to hand in a separate PDF writeup for this assignment.