I realize I’ve done this out of order, doing the final before this project, but a lot of the knowledge I acquired in doing so made this process very easy to understand. In accordance to my original proposal, I wanted…
MLAD: Final
For this project I wanted to allow the user to create their own dataset with p5/ml5 then display the results of the training of that dataset live. Originally I thought to use unet/bodypix to crop the person’s figure, but soon…
MLAD: A10
Link to images + video: https://drive.google.com/drive/folders/1OyU1jquV5yB2Q-GUbeRdOjjkznTKmNgZ?usp=sharing
MLAD: A9
https://drive.google.com/file/d/1jv2yFzKt3JY1v9PWy74zEdlqxGomrJ6O/view?usp=sharing For the dataset I decided to go with helicopters. Generally, one of my favorite genres of movie are war films, which includes a lot of Vietnam War movies. I feel like a shot of a helicopter passing overhead and…
MLAD: Week 2
Phone vs ID: https://editor.p5js.org/khx201/full/UOuDtjkk3 Random color circles for phone, purple/white squares for ID. Mask Detection: https://editor.p5js.org/khx201/full/Iw8z2VVZa Detects mask not worn, partially worn (on chin, nose not covered), and properly worn. Colored Chinese text in response to status (blank white if…
MLAD: Week 3
Voice Commands: https://editor.p5js.org/khx201/full/F920VE09y It works decently well for me, but it may be preferential to deeper (male) voices since the classmate I had contribute to the model was also male. Environment Sounds: https://editor.p5js.org/khx201/full/eiuURxfxY I wasn’t sure what theme I could…
MLAD: Assignment 1, DoodleNet Test & Reading Prompt Responses
Copying the code we did in class last week, I did a short test run with DoodleNet, keeping the camera in place but not necessarily remaining still, or even in frame just to see what the classifier would come up…