Skip to content

Latest commit

 

History

History
70 lines (61 loc) · 5.31 KB

guidelines.md

File metadata and controls

70 lines (61 loc) · 5.31 KB
Raw

Project Guidelines

Timeline

Event Date
Project allocation 12 October 2020
Project proposal submission 18 October 2020, 11:55 PM
Mid Evaluation 31 October 2020
Final Evaluation 19-25 November 2020

Project Proposal

Once the project is finalized, a project proposal needs to be submitted. The project proposal must include the following items (use images where possible):

  • Project ID and title
  • Link to GitHub repository
  • Team members
  • Main goal(s) of the project
  • Problem definition (What is the problem? How will things be done?)
  • Results of the project (What will be done? What is the expected result?)
  • What are the project milestones and expected timeline?
  • Is there a dataset that you require? How do you plan to get it?

We expect all members to have read the papers once, even if you did not completely understand all sections of the paper.

Deadline: 18 October 2020

Your respective TA would have a meeting with the team to give his feedback.

NOTE: Based on the contents of the proposal, your project plan may need to be modified. We will contact your team coordinator.

Managing your project

  • We will use GitHub Classrooms for the purpose of this project. TAs will make the project repositories for you.
  • The code for the project will need to be regularly updated on GitHub. Make sure to create a project and add yourselves as individual contributors to the projects. Also add your assigned TA to the repository. IMPORTANT: Add github repository link to project proposal.
  • To avoid running into GitHub’s size limits, ensure you upload only code and other documents (project proposal, final report) and NOT data (images). However, make sure that you upload them in either OneDrive or Google Drive, and share the link in the README of GitHub.
  • Periodically backup/update your code on GitHub. We will be checking for updates and grading based on them.
  • Contributions of each member will be seen by commits to the repository, so use you own GitHub accounts to contribute.
  • Also having commit clustered around a single day will look bad.

Progress Review

  • TAs will review the progress of your project in a mid-evaluation.
  • Details will be announced.

Final Submission and Presentation

Deliverables

You will have 3 deliverables:

  • Deliverable 1: Project Presentation (12+3=15 minutes)
    • Presentation + Demo (where appropriate)
    • Leave at least 3 minutes for questions from the audience.
    • TAs/Instructors may ask detailed questions, so everyone in the team should be familiar with the complete project, not just the part they worked on!
    • All team members must be present.
  • Deliverable 2: GitHub repository
    • Along with your code, add a README markdown file (markdown cheatsheet) which must contain:
      • Instructions on how to run your code and replicate the results.
      • Test your code on a machine different from that used during project development. Include any missing dependencies and how to resolve them in the README.
      • Link to input images: Package all images used for training/input to your code into a zip file. Upload this zip file and provide a link to this zip file.
      • Link to output images: Package all images obtained as output from your code into a zip file. Upload this zip file and provide a link to this zip file.
      • Use a sensible format for input and output filenames (e.g. On running code on input-0001.png, output should be output-0001.png). Alternately, you can include a script which loops through all your input images.
      • NOTE: Do NOT upload the input/output image zip files on your GitHub repository. Upload them elsewhere (OneDrive or Google Drive) and add their links to README.

Scoring Rubric

Component Weightage
Workload (Code), completeness and novelty 30%
Viva 40%
Presentation 30%

General Instructions

  • In any case, if you wish to have some feedback about the triviality or difficulty of your project, please speak to TAs or Instructor.
  • Your project work may contribute to your thesis/honors project, but the work you submit for this course must be done within the project submission deadline. It should be a separate deliverable. You may need your Honors/primary advisor’s approval for this.
  • You may use MATLAB/C/C++/Java/Python + any packages (OpenCV,ITK, etc) for your project. But merely invoking calls to someone else's software is not substance enough. ​ You should have your own non-trivial coding component.
  • If software for the research paper you implement is already available, you should use it only for comparison sake. You will be expected to implement the paper on your own. Please discuss with TAs/instructors if you need any clarifications for your specific case.
  • If your project is novel/new and you are planning to extend it towards a conference submission after the course is over, you must ensure that a significant portion is completed by project submission deadline time.