# k-means-yolo2

> k-means++ for YOLOv2

Latest version **1.0.0** (published 2020-02-29) · MIT license · 0 weekly downloads

## Install

```sh
npm install k-means-yolo2
pnpm add k-means-yolo2
yarn add k-means-yolo2
bun add k-means-yolo2
```

## Health

**Score 15/100 (F)** — status: abandoned.

Positive: no vulnerabilities.

Warnings: low downloads; no types; no esm support.

Negative: abandoned; low maintenance score.

## Facts

| | |
|---|---|
| Version | 1.0.0 |
| Published | 2020-02-29 |
| First published | 2020-02-29 |
| Weekly downloads | 0 |
| License | MIT |
| TypeScript types | none |
| Module format | CommonJS |
| Dependencies | 0 |
| Unpacked size | 534.1 KB |
| Known vulnerabilities | 0 |
| Install scripts | no |
| Author | weiyi |
| Maintainers | weiyi1994 |

## Links

- npm: https://www.npmjs.com/package/k-means-yolo2
- npm.io page: https://npm.io/package/k-means-yolo2

## Recent versions

- 1.0.0 (latest) — 2020-02-29

## README

<h1 align="center">yolo2-kmeans-plus 👋</h1>
<p>
  <img alt="Version" src="https://img.shields.io/badge/version-0.1.0-blue.svg?cacheSeconds=2592000" />
  <img src="https://img.shields.io/badge/npm-%3E%3D6.4.1-blue.svg" />
  <img src="https://img.shields.io/badge/node-%3E%3D8.12.0-blue.svg" />
  <a href="#" target="_blank">
    <img alt="License: MIT" src="https://img.shields.io/badge/License-MIT-yellow.svg" />
  </a>
</p>

> yolo2 keans++ nodejs package

## 环境

- npm >=6.4.1
- node >=8.12.0

### 介绍

> K均值聚类算法： 该算法用来给多个散列点分类， 在yolo中用来归类多个label类型，使得训练收敛更加快。支持KMeans ++初始化

<img src="./README/k-means.png" width="100%">

### 下载

```sh
npm install yolo2-kmeans-plus --save
```

### 使用

```javascript
import KMeans from "k-mean-yolo2";

// 实例化Kmeans
const k = new KMeans({
    w: 416,
    h: 416
}, labels, {
    n_anchors: 5,
    loss_convergence: 0.000001,
    iterations_num: 100,
    plus: true,
    debug: false
});

// =>
// centroids: (5) [{…}, {…}, {…}, {…}, {…}]
// iterations: 4
// loss: 3.774831882178467
// map: (4) [Array(5), Array(5), Array(5), Array(5)]
// startCentroids: (5) [{…}, {…}, {…}, {…}, {…}]
console.log(k.compute_centroids());

```

### 实例参数说明

|方法|效果|属性|
|----|-----|-----|
|`size`|[k-means尺寸](./README/size.md)|Object<{ w: number, h: number }>|
|`labels`|[标注数据](./README/labels.md)|Array<{ w: number, h: number, x: number, y: number }>|
|`configs`|[配置参数](./README/configs.md)|Object|

### API方法说明

|方法|效果|
|----|-----|
|`compute_centroids`|[获取K-Means计算结果](./README/compute_centroids.md)|

---
_Source: https://npm.io/package/k-means-yolo2 · Machine-readable twin of the npm.io package page. Health data is recomputed on every publish._