This is the final project for
DATA 622
, Fall 2016 at CUNY MS Data Analytics. Using the
[facial_expressions](https://github.com/muxspace/facial_expressions)
repository, run your trained model on the images in the
test
directory. You'll need to normalize the images in size and color space.
Project Submission
To get a grade on the Kaggle portion of the final, submit your solution file to Kaggle. On Blackboard, you need to submit your code for training (from the images directory) and evaluating on the test set. Using a notebook is allowed
if
you order the steps chronologically! Points will be deducted for any work that is difficult to follow.
In addition to the Kaggle submission, you are required to submit a short 3-4 page paper summarizing your work on Blackboard. The paper must discuss the following:
an overview of the problem;
why it's challenging;
what techniques you used;
comparison of performance;
generalizable lessons learned/takeaways.
Acknowledgements
The data in facial_expressions comes from a variety of sources, including
[Labeled Faces In The Wild](http://vis-www.cs.umass.edu/lfw/)
[The Japanese Female Facial Expression (JAFFE) Database](http://www.kasrl.org/jaffe.html)
[Indian Movie Face database (IMFDB)](http://cvit.iiit.ac.in/projects/IMFDB/)
[The Extended Yale Face Database B](http://vision.ucsd.edu/~iskwak/ExtYaleDatabase/ExtYaleB.html)