ml5js/ml5-library

[KNNClassifier/FeatureExtractor] Clarify docs

Open

#668 opened on Oct 30, 2019

View on GitHub
 (0 comments) (0 reactions) (0 assignees)JavaScript (6,136 stars) (905 forks)batch import
documentationfeature-extractorhelp wantedknn-classification

Description

Dear ml5 community,

I'm submitting a new issue. Please see the details below.

→ Step 1: Describe the issue 📝

Did you find a bug? Want to suggest an idea for feature?

  • enhancement
  • Update the documentation to clarify the difference between FeatureExtractor and KNNClassifier

I recently wrote to a friend:

Re transfer learning clarifications: Super short explanation: A. FeatureExtractor: creates a NEW neural network model (basically what the DIY neural network class is doing) on top of mobilenet. Need to clarify what "on top of" means in this case. B. KNNClassifier: the “addData” here is just taking the data from the user and then showing it to “mobilenet” to see what classes are most activated. This does NOT create a new model. It’s just saving the data so you can compare it against mobilenet later on.

Contributor guide

Tech stack
javascripttensorflow
Domain
documentationmachine learning
Issue type
documentation
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
clear
Prerequisites
basic understanding of machine learningfamiliarity with ml5.js
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
75
Research direction
The issue asks to update the documentation to clarify the difference between FeatureExtractor and KNNClassifier. Review the current documentation and code in the ml5 library repository (likely in the /docs or /examples folders). The issue body provides a short explanation that can be expanded: FeatureExtractor creates a new neural network model on top of MobileNet, while KNNClassifier saves data to compare against MobileNet without creating a new model. Write clear, concise documentation that explains these differences, aiming for beginners.