Summary
Keywords
Full Transcript
This video covers "KNN Classification." In this first part, I begin the process of building a "teachable machine"-style image classifier with ml5.js. Code: https://thecodingtrain.com/tracks/ml5js-beginners-guide/ml5/5-knn-classification/1-build-the-image-classifier 🕹️ p5.js Web Editor Sketch: https://editor.p5js.org/codingtrain/sketches/RERqlwJL 🎥 Previous: https://youtu.be/eU7gIy3xV30?list=PLRqwX-V7Uu6YPSwT06y_AEYTqIwbeam3y 🎥 Next: https://youtu.be/Mwo5_bUVhlA?list=PLRqwX-V7Uu6YPSwT06y_AEYTqIwbeam3y 🎥 All: https://www.youtube.com/playlist?list=PLRqwX-V7Uu6YPSwT06y_AEYTqIwbeam3y References: 💻 Teachable Machine: https://teachablemachine.withgoogle.com/ 💻 Machine Learning for the Web by Yining Shi: https://github.com/yining1023/machine-learning-for-the-web 📓 How to build a Teachable Machine with TensorFlow.js by Nikhil Thorat: https://observablehq.com/@nsthorat/how-to-build-a-teachable-machine-with-tensorflow-js 📓 MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications: https://arxiv.org/abs/1704.04861 Videos: 🚂 https://www.youtube.com/playlist?list=PLRqwX-V7Uu6YPSwT06y_AEYTqIwbeam3y Timestamps: 0:00 Introduction 1:16 Teachable Machine 2:22 Yining Shi's ml5 implementation of knn nearest neighbors 3:02 Nikhil Thorat's article on the Teachable Machine 3:43 knn classifier 4:20 MobileNet model 6:42 Softmax: normalizes data to give probabilities 8:25 logits - the "feature extractor" layer 10:52 Comparing two images 11:35 KNN nearest neighbors 12:35 Using the feature.infer function to get the logits 13:58 tensors 14:41 Using datasync to get the "digital finger print" of an image Editing by Mathieu Blanchette Animations by Jason Heglund Music from Epidemic Sound 🚂 Website: https://thecodingtrain.com/ 👾 Share Your Creation! https://thecodingtrain.com/guides/passenger-showcase-guide 🚩 Suggest Topics: https://github.com/CodingTrain/Suggestion-Box 💡 GitHub: https://github.com/CodingTrain 💬 Discord: https://thecodingtrain.com/discord 💖 Membership: http://youtube.com/thecodingtrain/join 🛒 Store: https://standard.tv/codingtrain 🖋️ Twitter: https://twitter.com/thecodingtrain 📸 Instagram: https://www.instagram.com/the.coding.train/ 🎥 https://www.youtube.com/playlist?list=PLRqwX-V7Uu6ZiZxtDDRCi6uhfTH4FilpH 🎥 https://www.youtube.com/playlist?list=PLRqwX-V7Uu6Zy51Q-x9tMWIv9cueOFTFA 🔗 p5.js: https://p5js.org 🔗 p5.js Web Editor: https://editor.p5js.org/ 🔗 Processing: https://processing.org 📄 Code of Conduct: https://github.com/CodingTrain/Code-of-Conduct This description was auto-generated. If you see a problem, please open an issue: https://github.com/CodingTrain/thecodingtrain.com/issues/new #knnclassification #machinelearningml #ml5js #p5js
