Reading:

Considering the Model and Data Biography reflect on the following questions:
- What questions do you still have about the model and the associated data? Are there elements you would propose including in the biography?
- How does understanding the provenance of the model and its data inform your creative process?

Question: What are the future plans (if any) of the data set? Is there a point of no return?

I think it’s would be beneficial to have a solid plan for the future of a project like this. Otherwise, the questions already written down and in the biographies cover the key points/important things to know about it. The who/what/when/where/why I think were really important to cover in the biography.

Like in the Humans of AI exhibition, understanding the origin of the data can result in exploring new or opposite points of view; stripping down the classification to the photo that caused the algorithm’s decision—essentially, moving “backwards” with the given data.

Coding Exercise:

Screen Recording 2022-09-29 at 10.52.21 PM.mov

Edit code OR fullscreen view

Process:

I didn’t have a set idea of what to do, so it feels a little similar to last week’s. It basically just uses the nose position as a pen/other drawing tool. The main points that I wanted to include were 1.) to keep the past positions of the nose to see what the user has already drawn and 2.) to be able to stop “drawing” and start up again later (to emulate picking a pen off paper).

I set it up first without using poseNet with an array and a toggle variable using mousePressed(). Adding in poseNet after that was relatively simple and I added in the ability to change colors just for fun.

Unfortunately, I couldn’t get the video to flip (keeps saying that the flipped video has no width/height and when I manually set a width/height it just doesn’t show). I also wanted to make the color change only apply to future circles and not the whole array (I think if I worked on it some more I could make it happen) but I couldn’t figure it out.