Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/zqingr/tfjs-yolov3
A Tensorflow js implementation of YOLOv3 and YOLOv3-tiny
https://github.com/zqingr/tfjs-yolov3
Last synced: 3 months ago
JSON representation
A Tensorflow js implementation of YOLOv3 and YOLOv3-tiny
- Host: GitHub
- URL: https://github.com/zqingr/tfjs-yolov3
- Owner: zqingr
- Created: 2018-08-01T08:47:15.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2023-02-28T13:19:23.000Z (almost 2 years ago)
- Last Synced: 2024-10-06T09:17:44.877Z (5 months ago)
- Language: TypeScript
- Homepage: https://zqingr.github.io/tfjs-yolov3-demo/
- Size: 11.8 MB
- Stars: 83
- Watchers: 3
- Forks: 16
- Open Issues: 10
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-yolo-object-detection - zqingr/tfjs-yolov3 - yolov3?style=social"/> : A Tensorflow js implementation of YOLOv3 and YOLOv3-tiny. (Other Versions of YOLO)
- awesome-yolo-object-detection - zqingr/tfjs-yolov3 - yolov3?style=social"/> : A Tensorflow js implementation of YOLOv3 and YOLOv3-tiny. (Other Versions of YOLO)
README
中文 | [English](./README_EN.md)
# tfjs-yolov3
## 介绍
完全用js来实现图片中的目标检测
基于yolov3算法和Tensorflow.js库
用tensorflow.js实现yolov3和yolov3-tiny
需要注意的是: 必须是[email protected]版本以上
## 特点
- 可以识别**任意尺寸**的图片
- 同时支持yolov3和yolov3-tiny
## 快速开始
### 安装
```
npm install tfjs-yolov3
```
### 用法示例
```javascript
import { yolov3, yolov3Tiny } from 'tfjs-yolov3'
async function start () {
const yolo = await yolov3Tiny() // pre-load model (35M)
// or
// const yolo = await yolov3() // pre-load model (245M)
const $img = document.getElementById('img')
const boxes = await yolo($img)
draw(boxes) // Some draw function
}
start()
```
## API 文档
yolov3和yolov3Tiny函数接受一个options对象，并返回一个函数
```typescript
export declare function yolov3 (
{ modelUrl, anchors }? :
{ modelUrl?: string, anchors?: number[] }
): Promise
export declare function yolov3Tiny (
{ modelUrl, anchors }? :
{ modelUrl?: string, anchors?: number[] }
): Promise
```
| 参数 | 说明 |
| ------------ | ------------ |
| modelUrl | 可选，预训练model的url，可把model下载到本地，加快预训练model的加载速度，[点我下载](https://github.com/zqingr/tfjs-yolov3/releases/tag/v1.0) |
| anchors | 可选，可自定义anchores，格式参考[config](https://github.com/zqingr/tfjs-yolov3/blob/master/src/yolo/config.js) |
这两个函数调用后会加载预训练model，并返回一个函数，可用这个函数去识别图片，并返回识别后的box列表，参数如下：
```typescript
type yolo = ($img: HTMLImageElement) => Promise
interface Box {
top: number
left: number
bottom: number
right: number
width: number
height: number
scores: number
classes: string
}
```
## DEMO
[点击查看在线DEMO](https://zqingr.github.io/tfjs-yolov3-demo/)
