- Understanding how to use pre-trained models other than image classification.
- Ability to work with PoseNet and ml5.js
- Ability to work with Object Detection Models (CoCoSSD).
- Ability to work with Image Segmentation models (UNet and BodyPix) and ml5.js.
- Week 3 Slides
- PoseNet
- Read Real-Time Human Pose Estimation in the Browser with TensorFlow.js by Dan Oved, with editing and illustrations by Irene Alvarado and Alexis Gallo.
- HandPose
- Object Detection
- UNet
- Trained by Zaid Alyafeai using mut1ny - Face/Head segmentation dataset
- BodyPix
- Slides from Ellen Nickles
- The Future Is Here!, a commission for The Photographers’ Gallery which examines the process of dataset creation by Mimi Ọnụọha
- Feminist Data Set tool kit to interrogate every step of the AI process by Caroline Sinders
- Ted Talk: The era of blind faith in big data must end and Cathy O'Neil's Risk Consulting & Algorithmic Auditing firm
- PoseNet Webcam Part Selection
- PoseNet Webcam Full Skeleton
- PoseNet Single Image
- Object Detection - CoCoSSD
- UNet Image Segmentation
- BodyPix Webcam
- Posnet
- Posnet Multiple Noses (Detect multiple poses, draw nose on each pose)
- Posenet Nose tail Save nose previous positions
- Posenet Vis Posenet, draw different visualized lines
- PoseNet Move the Stickman
- PoseNet with KNNClassification
- PoseNet with Teachable Machine
- PoseNet Video + Music
- PoseNet Video + Music + Multiple Squares
- PoseNet in Zoom, code, demo
- BodyPix
- BodyPix Parts
- BodyPix Parts Custom Color
- BodyPix Bubbles
- BodyPix Change Background
- UNET_webcam
- Maya Man's PoseNet sketchbook, Body, Movement, Language: A.I. Sketches with Bill T. Jones
- PoseNet Whack a Mole by Vibert Thio
- Sidewalk Orchestra by Cristóbal Valenzuela
- Pose Music by Tero Parviainen
- The Treachery of Sanctuary by Chris Milk
- Gait Analysis from runnersneed
- Moving morrir
- Sidewalk Orchestra
- Making music by posing melody shapes to my webcam
- Make music with Posenet from ml4a
- PoseNet in ml5.js
- Semi-Conductor
- Body, Movement, Language: AI Sketches With Bill T. Jones
- Touch Type
- nixel-Body
- DeepSquat
- Pose Animator
- Web Olympic
- AR Body Filter
- ballet rotoscope
- Bubbles with posenet
- Read Mixing movement and machine by Maya Man
- Read Humans of AI by Philipp Schmitt
- Pick one of the models above (PoseNet, HandPose, UNET, BodyPix, CoCoSSD) and following the examples and ml5.js documentation experiment with controlling elements of a p5.js sketch (color, geometry, sound, text) with the output of the model. (You may also choose a ml5.js model not covered here if you like!)
- https://editor.p5js.org/yining/sketches/W5MU2Xc02 (nose drawing)
- https://editor.p5js.org/yining/sketches/NhSshC1cq (pose + cat)
- https://editor.p5js.org/yining/sketches/jSnEyDrPw (Bodypix color )
- https://editor.p5js.org/yining/sketches/pVNmUDn-Z (Object detection)
- https://editor.p5js.org/yining/sketches/Tb4V-fXaz (trailing)
- https://editor.p5js.org/yining/sketches/_qolqm9Bo (Drawing)
- https://editor.p5js.org/yining/sketches/I_qrc4y6J (wrist growing rect)
- Considering the Model and Data Biography reflect on the 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?
- Document your response to the Data and Model biography as well as your p5.js sketch in a blog post and add a link to the post / your p5 sketch on the Assignment 3 Wiki. In your blog post, include visual documentation such as a recorded screen capture / video / GIFs of your sketch.