) 因此,让它开始吧。我想实现下一个想法:我想使用webrtc(交换视频和音频数据)与其他计算机上的其他用户建立联系,然后重新确定自己的情绪。因此,在这个项目中,我使用node-webrtc addon(这里是examples)。因此,我已经下载了示例并测试了视频合成示例,并且一切正常。 Here is result of testing
下一部分是我要识别面部表情。对于此任务,我使用face-api.js。我已经测试过此nice video。我不会附上照片,因为现在我正在使用ubuntu,但在Windows上对其进行了测试,只是相信我也可以正常工作。因此,现在是将两个模块结合在一起的时候了。
作为主项目,我使用node-webrtc示例,所有后续解释将围绕该模块进行。因此,要运行结果,您应该将weights文件夹从face-api复制到node-webrtc / examples / video-compositing文件夹中,然后仅替换下面的代码,而不是node-webrtc / example / video-compositing / server.js。
'use strict';
require('@tensorflow/tfjs-node');
const tf = require('@tensorflow/tfjs');
const nodeFetch = require('node-fetch');
const fapi = require('face-api.js');
const path = require('path');
const { createCanvas, createImageData } = require('canvas');
const { RTCVideoSink, RTCVideoSource, i420ToRgba, rgbaToI420 } = require('wrtc').nonstandard;
fapi.env.monkeyPatch({ fetch: nodeFetch });
const MODELS_URL = path.join(__dirname, '/weights');
const width = 640;
const height = 480;
Promise.all([
fapi.nets.tinyFaceDetector.loadFromDisk(MODELS_URL),
fapi.nets.faceLandmark68Net.loadFromDisk(MODELS_URL),
fapi.nets.faceRecognitionNet.loadFromDisk(MODELS_URL),
fapi.nets.faceExpressionNet.loadFromDisk(MODELS_URL)
]);
function beforeOffer(peerConnection) {
const source = new RTCVideoSource();
const track = source.createTrack();
const transceiver = peerConnection.addTransceiver(track);
const sink = new RTCVideoSink(transceiver.receiver.track);
let lastFrame = null;
function onFrame({ frame }) {
lastFrame = frame;
}
sink.addEventListener('frame', onFrame);
// TODO(mroberts): Is pixelFormat really necessary?
const canvas = createCanvas(width, height);
const context = canvas.getContext('2d', { pixelFormat: 'RGBA24' });
context.fillStyle = 'white';
context.fillRect(0, 0, width, height);
let emotion = '';
const interval = setInterval(() => {
if (lastFrame) {
const lastFrameCanvas = createCanvas(lastFrame.width, lastFrame.height);
const lastFrameContext = lastFrameCanvas.getContext('2d', { pixelFormat: 'RGBA24' });
const rgba = new Uint8ClampedArray(lastFrame.width * lastFrame.height * 4);
const rgbaFrame = createImageData(rgba, lastFrame.width, lastFrame.height);
i420ToRgba(lastFrame, rgbaFrame);
lastFrameContext.putImageData(rgbaFrame, 0, 0);
context.drawImage(lastFrameCanvas, 0, 0);
const emotionsArr = { 0: 'neutral', 1: 'happy', 2: 'sad', 3: 'angry', 4: 'fearful', 5: 'disgusted', 6: 'surprised' };
async function detectEmotion() {
let frameTensor3D = tf.browser.fromPixels(lastFrameCanvas)
let face = await fapi.detectSingleFace(frameTensor3D, new fapi.TinyFaceDetectorOptions()).withFaceExpressions();
//console.log(face);
function getEmotion(face) {
try {
let mostLikelyEmotion = emotionsArr[0];
let predictionArruracy = face.expressions[emotionsArr[0]];
for (let i = 0; i < Object.keys(face.expressions).length; i++) {
if (face.expressions[emotionsArr[i]] > predictionArruracy && face.expressions[emotionsArr[i]] < 1 ){
mostLikelyEmotion = emotionsArr[i];
predictionArruracy = face.expressions[emotionsArr[i]];
}
}
return mostLikelyEmotion;
}
catch (e){
return '';
}
}
let emot = getEmotion(face);
return emot;
}
detectEmotion().then(function(res) {
emotion = res;
});
} else {
context.fillStyle = 'rgba(255, 255, 255, 0.025)';
context.fillRect(0, 0, width, height);
}
if (emotion != ''){
context.font = '60px Sans-serif';
context.strokeStyle = 'black';
context.lineWidth = 1;
context.fillStyle = `rgba(${Math.round(255)}, ${Math.round(255)}, ${Math.round(255)}, 1)`;
context.textAlign = 'center';
context.save();
context.translate(width / 2, height);
context.strokeText(emotion, 0, 0);
context.fillText(emotion, 0, 0);
context.restore();
}
const rgbaFrame = context.getImageData(0, 0, width, height);
const i420Frame = {
width,
height,
data: new Uint8ClampedArray(1.5 * width * height)
};
rgbaToI420(rgbaFrame, i420Frame);
source.onFrame(i420Frame);
});
const { close } = peerConnection;
peerConnection.close = function() {
clearInterval(interval);
sink.stop();
track.stop();
return close.apply(this, arguments);
};
}
module.exports = { beforeOffer };
这是results1,result2和result3,它们都可以正常工作))...好吧,不,在2-3分钟后,我的计算机停止执行任何操作,我什至无法移动鼠标,然后在终端中出现错误“ Killed”。我读到有关此错误here的信息,因为我只更改了项目中的一个脚本,所以我怀疑代码中的某个地方存在数据泄漏,并且随着时间的流逝,我的RAM越来越满。有人可以帮我解决这个问题吗?为什么程序以杀死进程结束?如果有人要自己测试,我将保留json包以轻松安装所有要求。
{
"name": "node-webrtc-examples",
"version": "0.1.0",
"description": "This project presents a few example applications using node-webrtc.",
"private": true,
"main": "index.js",
"scripts": {
"lint": "eslint index.js examples lib test",
"start": "node index.js",
"test": "npm run test:unit && npm run test:integration",
"test:unit": "tape 'test/unit/**/*.js'",
"test:integration": "tape 'test/integration/**/*.js'"
},
"keywords": [
"Web",
"Audio"
],
"author": "Mark Andrus Roberts <markandrusroberts@gmail.com>",
"license": "BSD-3-Clause",
"dependencies": {
"@tensorflow/tfjs": "^1.2.9",
"@tensorflow/tfjs-core": "^1.2.9",
"@tensorflow/tfjs-node": "^1.2.9",
"Scope": "github:kevincennis/Scope",
"body-parser": "^1.18.3",
"browserify-middleware": "^8.1.1",
"canvas": "^2.6.0",
"color-space": "^1.16.0",
"express": "^4.16.4",
"face-api.js": "^0.21.0",
"node-fetch": "^2.3.0",
"uuid": "^3.3.2",
"wrtc": "^0.4.1"
},
"devDependencies": {
"eslint": "^5.15.1",
"tape": "^4.10.0"
}
}
如果您遇到诸如“ someFunction不是函数”之类的错误或类似之类的错误,可能是因为您需要安装@ tensorflow / tfjs-core,tfjs和tfjs-node 1.2.9版本。像npm一样,我@ tensorflow / tfjs-core @ 1.2.9。对于所有3个程序包。感谢您的回答和理解))
答案 0 :(得分:0)
在这一年中,我使用faceapi.js和tensorflow.js,我测试了您的代码及其正常运行,但是在不到一分钟的时间内将我的RAM增加到了2GB,这会导致内存泄漏,使用Tensor时应该释放记忆?你好吗?
但是您应该在节点to inspect memory leak 中使用--inspect arg
仅通话:
frameTensor3D.dispose();
我重构了您的代码并与您分享,希望对您有所帮助
"use strict";
require("@tensorflow/tfjs-node");
const tf = require("@tensorflow/tfjs");
const nodeFetch = require("node-fetch");
const fapi = require("face-api.js");
const path = require("path");
const { createCanvas, createImageData } = require("canvas");
const {
RTCVideoSink,
RTCVideoSource,
i420ToRgba,
rgbaToI420
} = require("wrtc").nonstandard;
fapi.env.monkeyPatch({ fetch: nodeFetch });
const MODELS_URL = path.join(__dirname, "/weights");
const width = 640;
const height = 480;
Promise.all([
fapi.nets.tinyFaceDetector.loadFromDisk(MODELS_URL),
fapi.nets.faceLandmark68Net.loadFromDisk(MODELS_URL),
fapi.nets.faceRecognitionNet.loadFromDisk(MODELS_URL),
fapi.nets.faceExpressionNet.loadFromDisk(MODELS_URL)
]);
function beforeOffer(peerConnection) {
const source = new RTCVideoSource();
const track = source.createTrack();
const transceiver = peerConnection.addTransceiver(track);
const sink = new RTCVideoSink(transceiver.receiver.track);
let lastFrame = null;
function onFrame({ frame }) {
lastFrame = frame;
}
sink.addEventListener("frame", onFrame);
// TODO(mroberts): Is pixelFormat really necessary?
const canvas = createCanvas(width, height);
const context = canvas.getContext("2d", { pixelFormat: "RGBA24" });
context.fillStyle = "white";
context.fillRect(0, 0, width, height);
const emotionsArr = {
0: "neutral",
1: "happy",
2: "sad",
3: "angry",
4: "fearful",
5: "disgusted",
6: "surprised"
};
async function detectEmotion(lastFrameCanvas) {
const frameTensor3D = tf.browser.fromPixels(lastFrameCanvas);
const face = await fapi
.detectSingleFace(
frameTensor3D,
new fapi.TinyFaceDetectorOptions({ inputSize: 160 })
)
.withFaceExpressions();
//console.log(face);
const emo = getEmotion(face);
frameTensor3D.dispose();
return emo;
}
function getEmotion(face) {
try {
let mostLikelyEmotion = emotionsArr[0];
let predictionArruracy = face.expressions[emotionsArr[0]];
for (let i = 0; i < Object.keys(face.expressions).length; i++) {
if (
face.expressions[emotionsArr[i]] > predictionArruracy &&
face.expressions[emotionsArr[i]] < 1
) {
mostLikelyEmotion = emotionsArr[i];
predictionArruracy = face.expressions[emotionsArr[i]];
}
}
//console.log(mostLikelyEmotion);
return mostLikelyEmotion;
} catch (e) {
return "";
}
}
let emotion = "";
const interval = setInterval(() => {
if (lastFrame) {
const lastFrameCanvas = createCanvas(lastFrame.width, lastFrame.height);
const lastFrameContext = lastFrameCanvas.getContext("2d", {
pixelFormat: "RGBA24"
});
const rgba = new Uint8ClampedArray(
lastFrame.width * lastFrame.height * 4
);
const rgbaFrame = createImageData(
rgba,
lastFrame.width,
lastFrame.height
);
i420ToRgba(lastFrame, rgbaFrame);
lastFrameContext.putImageData(rgbaFrame, 0, 0);
context.drawImage(lastFrameCanvas, 0, 0);
detectEmotion(lastFrameCanvas).then(function(res) {
emotion = res;
});
} else {
context.fillStyle = "rgba(255, 255, 255, 0.025)";
context.fillRect(0, 0, width, height);
}
if (emotion != "") {
context.font = "60px Sans-serif";
context.strokeStyle = "black";
context.lineWidth = 1;
context.fillStyle = `rgba(${Math.round(255)}, ${Math.round(
255
)}, ${Math.round(255)}, 1)`;
context.textAlign = "center";
context.save();
context.translate(width / 2, height);
context.strokeText(emotion, 0, 0);
context.fillText(emotion, 0, 0);
context.restore();
}
const rgbaFrame = context.getImageData(0, 0, width, height);
const i420Frame = {
width,
height,
data: new Uint8ClampedArray(1.5 * width * height)
};
rgbaToI420(rgbaFrame, i420Frame);
source.onFrame(i420Frame);
});
const { close } = peerConnection;
peerConnection.close = function() {
clearInterval(interval);
sink.stop();
track.stop();
return close.apply(this, arguments);
};
}
module.exports = { beforeOffer };
对不起,我的英语,祝你好运