Hands-On Python Deep Learning for the Web

Creating a TF.js model

Let's begin by reading the data we have stored in the iris variable to a tensor2d object:

1. In your index.js file, add the following code:

const trainingData = tf.tensor2d(iris.map(item=> [    item.sepal_length, item.sepal_width, item.petal_length, item.petal_width]),[144,4])

We do not have any test data yet; this will be provided by the user.

2. Next, we create a one-hot encoding of the possible three varieties of flowers:

const outputData = tf.tensor2d(iris.map(item => [    item.species === 'setosa' ? 1 : 0,    item.species === 'virginica' ? 1 : 0,    item.species === 'versicolor' ? 1 : 0]), [144,3])

We are now ready to create the model for training. The following code might remind you of the code we used in the previous chapter ...