Handmade Dataset

Final Project

Description

You and your team will create a training dataset of images together throughout the rest of the semester. At the end of the semester, we will train a Generative Adversarial Network on your dataset. You will not be assessed on the results of the GAN, but rather the thoughtfulness, care, and consideration of your dataset creation process. You will need to have at least 800 images within your dataset so please take that into consideration when developing your project idea. **The more homogenous your images are, the "better" your GAN will work. The more diverse your images are, the more images you will need to get an output that resembles the input images. Because of this, I am limiting your subject matter/ideas to that which can fit within our "photo station" and be photographed/filmed on a consistant black or white background. So your subject matter should be able to fit on a table top space of 15" x 15."

Technical Specifications:

Tips:

Submission schedule:

Link to dataset folders: Folders

Photo Station Sign-up sheet: link

Inspo: