1.2.3 • Published 2 years ago

@paddlejs-models/humanseg v1.2.3

Weekly downloads
180
License
ISC
Repository
-
Last release
2 years ago

中文版

humanseg

A real-time human-segmentation model. You can use it to change background. The output of the model is gray value. Model supplies simple api for users.

Api drawHumanSeg can draw human segmentation with a specified background. Api blurBackground can draw human segmentation with a blurred origin background. Api drawMask can draw the background without human.

Run Demo

  1. Execute in the current directory
npm install
npm run dev
  1. Visit http://0.0.0.0:8866
  2. Visit gpu pipeline http://0.0.0.0:8866/gpu.html

Usage

import * as humanseg from '@paddlejs-models/humanseg';

// load humanseg model, use 398x224 shape model, and preheat
await humanseg.load();

// use 288x160 shape model, preheat and predict faster with a little loss of precision
// await humanseg.load(true, true);

// get the gray value [2, 398, 224] or [2, 288, 160];
const { data } = await humanseg.getGrayValue(img);

// background canvas
const back_canvas = document.getElementById('background') as HTMLCanvasElement;

// draw human segmentation
const canvas1 = document.getElementById('back') as HTMLCanvasElement;
humanseg.drawHumanSeg(data, canvas1, back_canvas) ;

// blur background
const canvas2 = document.getElementById('blur') as HTMLCanvasElement;
humanseg.drawHumanSeg(data, canvas2) ;

// draw the mask with background
const canvas3 = document.getElementById('mask') as HTMLCanvasElement;
humanseg.drawMask(data, canvas3, back_canvas);

gpu pipeline

// 引入 humanseg sdk
import * as humanseg from '@paddlejs-models/humanseg/lib/index_gpu';

// load humanseg model, use 398x224 shape model, and preheat
await humanseg.load();

// use 288x160 shape model, preheat and predict faster with a little loss of precision
// await humanseg.load(true, true);


// background canvas
const back_canvas = document.getElementById('background') as HTMLCanvasElement;

// draw human segmentation
const canvas1 = document.getElementById('back') as HTMLCanvasElement;
await humanseg.drawHumanSeg(input, canvas1, back_canvas) ;

// blur background
const canvas2 = document.getElementById('blur') as HTMLCanvasElement;
await humanseg.drawHumanSeg(input, canvas2) ;

// draw the mask with background
const canvas3 = document.getElementById('mask') as HTMLCanvasElement;
await humanseg.drawMask(input, canvas3, back_canvas);

Online experience

image human segmentation:https://paddlejs.baidu.com/humanseg

video-streaming human segmentation:https://paddlejs.baidu.com/humanStream

Performance

Used in Video Meeting

1.2.3

2 years ago

1.2.2

2 years ago

1.2.1

2 years ago

1.2.0

2 years ago

1.1.6

2 years ago

1.1.5

2 years ago

1.1.4

2 years ago

1.1.3

2 years ago

1.1.2

2 years ago

1.1.1

3 years ago

1.1.0

3 years ago

1.0.5

3 years ago

1.0.4

3 years ago

1.0.3

3 years ago

1.0.2

3 years ago

1.0.2-0

3 years ago

1.0.1-3

3 years ago

1.0.1-2

3 years ago

1.0.1-1

3 years ago

1.0.0

3 years ago

1.0.1-0

3 years ago

0.0.8

3 years ago

0.0.7

3 years ago

0.0.6

3 years ago

0.0.5

3 years ago

0.0.4

3 years ago

0.0.3

3 years ago

0.0.2

3 years ago

0.0.1

3 years ago