ml5.js Weight file with basename is not provided issue

[romario32]

Code

` let trained = false; let collecting = false; let video; let poseNet; let pose; let skeleton; let brain; let state = 'waiting'; let targeLabel = 'pose'; let poselist let poseLabel = "Do your pose"; let count = 0;

function setup() { canvas = createCanvas(640, 480); canvas.parent('sketch'); video = createCapture(VIDEO); video.hide(); poseNet = ml5.poseNet(video, modelLoaded); poseNet.on('pose', gotPoses); let options = { inputs: 34, outputs: 2, task: 'classification', debug: true }

brain = ml5.neuralNetwork(options);
// Buttons
if (poseMode == "signup") {
    select('#collectWrongData').mousePressed(wrong);
    select('#collectData').mousePressed(correct);
    select('#trainData').mousePressed(trainModel);

} else if (poseMode == "login") {
    const modelInfo = {
        model: public_path1,
        metadata: public_path2,
        weights: public_path3,
    };
    brain.load(modelInfo, brainLoaded);
}

}

function wrong() { doPose('F'); }

function correct() { doPose('P'); } //login Mode function brainLoaded() { console.log('pose classification ready!'); classifyPose(); }

function classifyPose() { if (pose) { let inputs = []; for (let i = 0; i < pose.keypoints.length; i++) { let x = pose.keypoints[i].position.x; let y = pose.keypoints[i].position.y; inputs.push(x); inputs.push(y); } brain.classify(inputs, gotResult); } else { setTimeout(classifyPose, 100); } }

function gotResult(error, results) {

if (results[0].confidence > 0.75) {
    poseLabel = results[0].label.toUpperCase();
}
//console.log(results[0].confidence);
classifyPose();

}

//signup Mode function gotPoses(poses) { // console.log(poses); if (poses.length > 0) { pose = poses[0].pose; skeleton = poses[0].skeleton; if (state == 'collecting') { let inputs = []; for (let i = 0; i < pose.keypoints.length; i++) { let x = pose.keypoints[i].position.x; let y = pose.keypoints[i].position.y; inputs.push(x); inputs.push(y); } let target = [targetLabel]; brain.addData(inputs, target); } } }

function doPose(type) { targetLabel = type; console.log(targetLabel); timer('waitTime'); setTimeout(function () { timer('poseTimer'); console.log('collecting'); state = 'collecting'; setTimeout(function () { console.log('not collecting'); state = 'waiting'; }, 10000); }, 10000);

}

function trainModel() { // No longer collecting dataa brain.normalizeData(); let options = { epochs: 50 } brain.train(options, finishedTraining); }

function finishedTraining() { console.log('done'); brain.save(poseID); }

//timer function startTimer(duration, display) { var timer = duration, minutes, seconds; var idTime = setInterval(function () { minutes = parseInt(timer / 60, 10) seconds = parseInt(timer % 60, 10);

    minutes = minutes < 10 ? "0" + minutes : minutes;
    seconds = seconds < 10 ? "0" + seconds : seconds;

    display.textContent = minutes + ":" + seconds;

    if (timer == 0) {
        clearInterval(idTime);
    }

    if (--timer < 0) {
        timer = duration;
    }
}, 1000);

}

function timer(t) { var fiveMinutes = 10, display = document.querySelector('#' + t); startTimer(fiveMinutes, display); }

function modelLoaded() { console.log('poseNet ready');

if (poseMode == "login" && count == 0) {
    count++;
    setup();
}

}

//skeleton display function draw() { push(); translate(video.width, 0); scale(-1, 1); image(video, 0, 0, video.width, video.height);

if (pose) {
    for (let i = 0; i < skeleton.length; i++) {
        let a = skeleton[i][0];
        let b = skeleton[i][1];
        strokeWeight(2);
        stroke(0);

        line(a.position.x, a.position.y, b.position.x, b.position.y);
    }
    for (let i = 0; i < pose.keypoints.length; i++) {
        let x = pose.keypoints[i].position.x;
        let y = pose.keypoints[i].position.y;
        fill(0);
        stroke(255);
        ellipse(x, y, 16, 16);
    }
}
pop();

if (poseMode == "login") {
    fill(255, 0, 255);
    noStroke();
    textSize(30);
    textAlign(CENTER, CENTER);
    text(poseLabel, width / 2, height / 2);
}

} `

I am trying to train a model on one screen and deploy the model on another in laravel. i got the model to train however when I am trying to estimate a pose it won't work. I am plagued by this error:

ml5.min.js:18 Uncaught (in promise) Error: Weight file with basename 'modeltest.weights.bin' is not provided. at ml5.min.js:18 at Array.forEach () at t.checkManifestAndWeightFiles (ml5.min.js:18) at FileReader.o.onload (ml5.min.js:18)

[romario32]

I found the issue, it seems like the model doesn't work when ml5.neuralNetwork(options).save(poseID); is given a string.

[TheoKVA]

I came here with google search.

romario got it. If anybody gets the same error "Weight file with basename is not provided" the solution is easy : do not save your model with a custom name => USE model.save(), NOT model.save("myName")

Then us the newly generated files "model.weights.bin"

Works like a charm.