How to use the @tensorflow/tfjs-node.tensor2d function in @tensorflow/tfjs-node

[model, encoder, decoder] = ae_model.buildModel(modelParams)
encoder.summary()
decoder.summary()
model.summary()



console.log(" >> Train/Test Split | Train:", trainEcg.length, " Test:", testEcg.length);
// console.log(" >> Features per data point ", ecg[0].data.length)
// console.log(trainEcg[0]);


const xs = tf.tensor2d(trainEcg.map(item => item.data
), [trainEcg.length, trainEcg[0].data.length])

const xsTest = tf.tensor2d(testEcg.map(item => item.data
), [testEcg.length, testEcg[0].data.length])

yTest = testEcg.map(item => item.target + "" === 1 + "" ? 0 : 1)



// console.log(xs, xsTest);


async function train_data(model) {
    for (let i = 0; i < numSteps; i++) {
        startTime = new Date();
        const res = await model.fit(xs,
            xs, { epochs: numEpochs, verbose: 0, batchSize: batchSize, validationData: [xsTest, xsTest] });
        endTime = new Date();
        elapsedTime = (endTime - startTime) / 1000

function convertToTensors(featuresData, labelData, testSplit) {
  if (featuresData.length !== labelData.length) {
    throw new Error('features set and labels set have different numbers of examples');
  }

  const [shuffledFeatures, shuffledLabels] = shuffleData(featuresData, labelData);

  const featuresTensor = tf.tensor2d(shuffledFeatures, [numSamplesPerGesture, totalNumDataPerFile]);

  // Create a 1D `tf.Tensor` to hold the labels, and convert the number label
  // from the set {0, 1, 2} into one-hot encoding (.e.g., 0 --> [1, 0, 0]).
  const labelsTensor = tf.oneHot(tf.tensor1d(shuffledLabels).toInt(), numClasses);

  return split(featuresTensor, labelsTensor, testSplit);
}

// The dataset has 4177 rows. Split them into 2 groups, one for training and
  // one for validation. Take about 3500 rows as train dataset, and the rest as
  // validation dataset.
  const trainBatches = Math.floor(3500 / batchSize);
  const dataset = datasetObj.dataset.shuffle(1000).batch(batchSize);
  const trainDataset = dataset.take(trainBatches);
  const validationDataset = dataset.skip(trainBatches);

  await model.fitDataset(
      trainDataset, {epochs: epochs, validationData: validationDataset});

  await model.save(savePath);

  const loadedModel = await tf.loadLayersModel(savePath + '/model.json');
  const result = loadedModel.predict(
      tf.tensor2d([[0, 0.625, 0.495, 0.165, 1.262, 0.507, 0.318, 0.39]]));
  console.log(
      'The actual test abalone age is 10, the inference result from the model is ' +
      result.dataSync());
}

function convertToTensors(featuresData, labelData, testSplit) {
  if (featuresData.length !== labelData.length) {
    throw new Error('features set and labels set have different numbers of examples');
  }

  const [shuffledFeatures, shuffledLabels] = shuffleData(featuresData, labelData);

  const featuresTensor = tf.tensor2d(shuffledFeatures, [numSamplesPerGesture, totalNumDataPerFile]);

  // Create a 1D `tf.Tensor` to hold the labels, and convert the number label
  // from the set {0, 1, 2} into one-hot encoding (.e.g., 0 --> [1, 0, 0]).
  const labelsTensor = tf.oneHot(tf.tensor1d(shuffledLabels).toInt(), numClasses);

  return split(featuresTensor, labelsTensor, testSplit);
}

// const tf = require('@tensorflow/tfjs');
const _ = require('lodash');
const tf = require('@tensorflow/tfjs-node');

iris = require("./data/iris.json")
iris = _.shuffle(iris)
iris_train = iris.slice(0, 130)
iris_test = iris.slice(130, iris.length)

const trainingData = tf.tensor2d(iris_train.map(item => [
    item.sepalLength, item.sepalWidth, item.petalLength, item.petalWidth
]
), [iris_train.length, 4])

const testData = tf.tensor2d(iris_test.map(item => [
    item.sepalLength, item.sepalWidth, item.petalLength, item.petalWidth
]
), [iris_test.length, 4])

const outputData = tf.tensor2d(iris_train.map(item => [
    item.species === 'setosa' ? 1 : 0,
    item.species === 'virginica' ? 1 : 0,
    item.species === 'versicolor' ? 1 : 0

]), [iris_train.length, 3])

stockapi.getStockHistoricalDaily($stock, (data) => {

        prices = data[0];
        let min = Math.min.apply(null, prices);
        let max = Math.max.apply(null, prices);
        prices = prices.map((el) => minMaxScaler(el, min, max));
        dates = data[1];
        var lookbackPrices = [];
        var targets = [];
        for (let index = 10; index < prices.length; index++) {
            lookbackPrices[index - 10] = prices.slice(index - 10, index);
            targets.push(prices[index]);
        }
        tfPrices = tf.tensor2d(lookbackPrices);
        global.pred = tf.tensor2d(lookbackPrices[0], [1, 10]);
        global.pred = tf.reshape(global.pred, [1, 10, 1]);
        tfTargets = tf.tensor1d(targets);
        tfPrices = tf.reshape(tfPrices, [prices.length - 10, 10, 1]);
        //tfPrices.print();
        //tfTargets.print();


        const model = tf.sequential();
        model.add(tf.layers.lstm({ units: 32, inputShape: [10, 1] }));
        model.add(tf.layers.dense({ units: 1, activation: 'linear' }));
        $lr = parseFloat($('#txtLearningRate').val());
        const lr = $lr;
        const opt = tf.train.adam(lr);
        const loss = 'meanSquaredError';
        openSnackbar("Compiling model");
        model.compile({ optimizer: opt, loss: loss, metrics: ['mae', 'mse'] }); /* Using Mean Absolute Error as metrics for accuracy of model */

const outputs = [];
    for (let ix = 0; ix < trainLabels.length; ix++) {
        const output = [0, 0, 0, 0, 0, 0, 0, 0, 0, 0];
        output[trainLabels[ix]] = 1;
        outputs.push(output);
    }
    const trainLabelsTensor = tf.tensor2d(outputs);

    const testOutputs = [];
    for (let ix = 0; ix < testLabels.length; ix++) {
        const output = [0, 0, 0, 0, 0, 0, 0, 0, 0, 0];
        output[testLabels[ix]] = 1;
        testOutputs.push(output);
    }
    const testLabelsTensor = tf.tensor2d(testOutputs);

    const model = createConvModel();

    model.compile({
        optimizer: 'rmsprop',
        loss: 'categoricalCrossentropy',
        metrics: ['accuracy'],
    });

    const batchSize = 320;
    const trainEpochs = 20;

    await model.fit(trainDigitsTensor, trainLabelsTensor, {
        batchSize,
        validationData: [testDigitsTensor, testLabelsTensor],
        shuffle: true,

]
), [iris_train.length, 4])

const testData = tf.tensor2d(iris_test.map(item => [
    item.sepalLength, item.sepalWidth, item.petalLength, item.petalWidth
]
), [iris_test.length, 4])

const outputData = tf.tensor2d(iris_train.map(item => [
    item.species === 'setosa' ? 1 : 0,
    item.species === 'virginica' ? 1 : 0,
    item.species === 'versicolor' ? 1 : 0

]), [iris_train.length, 3])

const y_test = tf.tensor2d(iris_test.map(item => [
    item.species === 'setosa' ? 1 : 0,
    item.species === 'virginica' ? 1 : 0,
    item.species === 'versicolor' ? 1 : 0

]), [iris_test.length, 3])

const model = tf.sequential();

model.add(tf.layers.dense({
    inputShape: [4],
    activation: "sigmoid",
    units: 10,
    name: "layer1"
}))

model.add(tf.layers.dense({

const testLabels = await mnist.getTestLabels();
    const testDigits = await mnist.getTestImages();

    const trainDigitsTensor = tf.tensor4d(trainDigits.map(mnist.normalize),
        [trainDigits.length / (28 * 28), 28, 28, 1]);

    const testDigitsTensor = tf.tensor4d(testDigits.map(mnist.normalize),
        [testDigits.length / (28 * 28), 28, 28, 1]);

    const outputs = [];
    for (let ix = 0; ix < trainLabels.length; ix++) {
        const output = [0, 0, 0, 0, 0, 0, 0, 0, 0, 0];
        output[trainLabels[ix]] = 1;
        outputs.push(output);
    }
    const trainLabelsTensor = tf.tensor2d(outputs);

    const testOutputs = [];
    for (let ix = 0; ix < testLabels.length; ix++) {
        const output = [0, 0, 0, 0, 0, 0, 0, 0, 0, 0];
        output[testLabels[ix]] = 1;
        testOutputs.push(output);
    }
    const testLabelsTensor = tf.tensor2d(testOutputs);

    const model = createConvModel();

    model.compile({
        optimizer: 'rmsprop',
        loss: 'categoricalCrossentropy',
        metrics: ['accuracy'],
    });