TrainAModel

Week 4 Train a model with Tensorflow Lite / Tensorflow.js / ml5.js

Slides

Notes:

• Understand the full story of building a ML model for classification or regression.
• Understand how data is formatted and downloaded including CSV and JSON.
• Consider how to frame the problem and collect data.
• Learn how to prepare a dataset, including how to normalize and properly format it.

Workshop:

• Training your own gesture classifier,
  • Gestures to Emoji, Guide
  • ABC Gestures to 3 LEDs, Guide
• Training hand pose model
  • Hand pose tracking + KNN Classification, p5 web editor code, demo video
  • Hand pose tracking + Neural Network, demo video
    • Collect data
    • Train the model
    • Run the model

Resource:

• TinyML Workshop
• TinyML Book chapter 12: Magic Wand, Training a model(Log in with your NYU NetId)
• Coding training video: ml5 pose classifier
  • ml5.js: Pose Classification training all steps
  • NeuralNetwork pose classifier