EECS 442: Computer Vision (Winter 2022)


The goal of this assignment is to incentivize learning to write reasonably good python/numpy code. This is so that:

  • You don’t learn it on your own and discover some super useful function at the end of the semester

  • If you’re doing something like calculating eigenvectors wrong, you find out in a low-stakes way

  • You get credit for spending time doing this

If you need an introduction to Python or numpy, you can check out this tutorial. We'll additionally cover this in discussions and have a more thorough guide and introduction released soon with discussions.

I highly recommend this linear algebra review and reference. (At least for for this class) you don’t need to know:

  • determinants (you may see them once – a rotation has a determinant of 1)

  • quadratic forms and positive-definiteness

  • fun facts about eigenvectors and eigenvalues – just the Ax = lx for x != 0

  • the Hessian

  • Eigenvalues as Optimization.

That said, some of these is quite useful in other areas and appears in ML.

Homework Files

To get the homework, please confirm that you have read the the rules for collaboration.

Click the button to reveal the links