Final Project
CSCI 1430: Introduction to Computer Vision
Logistics
- Part 1: Proposal
- LaTeX Template
- Hand-in process: Gradescope as PDF.
- Part 2: Progress report 1 / TA check in
- LaTeX Template
- Hand-in process: Gradescope as PDF.
- Part 3: Progress report 2 / TA check in
- LaTeX Template
- Hand-in process: Gradescope as PDF.
- Part 4: Two-minute presentations
- Due: In class; see schedule on Piazza.
- Part 5: Project report and code
- LaTeX Template (CVPR style)
- Hand-in process: Gradescope as a Github repository. Include your code, report, and any other materials. If you have more than 200 files or excessively large files, please link externally.
Overview
Slide deck from class: Google Slides
Grading
Grading is holistic: we will use a combination of scores from the presentation and report and code. Grading is not on a curve. Each project will be judged in a review-panel-style grading session, where proposals will be reviewed by multiple course staff and then discussed.
| Component | Percent | Proposal | 3.33% |
|---|---|
| Progress report 1 | 3.33% |
| Progress report 2 | 3.33% |
| Presentation/report/code | 90% |
Workload
The project is expected to take four weeks of time for up to four people. So, at 12 hours per week per person that comes out to ~192 hours of work for a four person team.
Capstone: For those of you completing the course as a capstone, we expect you to put a commensurate amount of additional effort into the final project as per the extra credit for the other projects, e.g., an additional 2–4 hours per week. Given the wide scope of the projects, it is difficult to tie this to a specific feature or work component, but feel free to talk to your TA to discuss any plans.
Compute
The Brown CS Grid is a collection of computers that can be accessed via any department machines. Please note that these machines are used for CS Research and as so please be respectful of the resources when using them. The GRID has both GPUs and CPUs available to use. If you need any Python libraries that do not exist on department machines either create a virtualenv or install the libraries in your home folder using the --user option for pip.
- Read the Grid Quickstart Guide Grid Quickstart Guide
- Grid GPU Example
- To run the following example, run
- qsub -N 'name of your JOB' run_GRID_gpu.sh $PYTHON_FILE $ARGS
- qstat to view currently running jobs
- qdel $JOB_ID to kill or cancel one of your jobs. $JOB_ID can be obtained from qstat
Help
If you need anything, then please ask your TA. We don't know quite what you will attempt or need, but we have some camera equipment and other hardware available for your projects.
Previous Final Projects:
- Fall 2017: Webgazer