data scientist at codescene
Public
Edited
Aug 28, 2024
train = generateData(100)
XX = tf.tensor2d([[1,2,3],[4,5,6]])
model = {
// Create model, add layers.
const model = tf.sequential()
model.add(tf.layers.dense({
units: 2,
inputShape: [3]
}))
model.compile({
loss: 'meanSquaredError',
optimizer: 'sgd'
})
// Train model.
const [X, y] = train
model.fit(X, y, {
epochs: 100
})
//model.add(tf.layers.dense({units: 1, inputShape: [1]}));
// Model loss.
//model.compile({loss: 'meanSquaredError', optimizer: 'sgd'});
// Syntetic data.
//const xs = tf.tensor2d([-1, 0, 1, 2, 3, 4], [6, 1]);
//const ys = tf.tensor2d([-3, -1, 1, 3, 5, 7], [6, 1]);
//model.fit(xs, ys, {epochs: 250});
return model
}
paramTypes = xTypes.map(generateParams)
function truncateLayer(x) {
// Extract mu and sigma.
let [mus, sigmas] = x.unstack(1)
// Expand dimensions
mus = mus.expandDims(1)
sigmas = sigmas.expandDims(1)
// Apply activations.
mus = tf.sigmoid(mus)
sigmas = tf.softplus(sigmas)
}
tf.sigmoid(MU)
tf = require("@tensorflow/tfjs")
ran = require("ranjs")
One platform to build and deploy the best data apps
Experiment and prototype by building visualizations in live JavaScript notebooks. Collaborate with your team and decide which concepts to build out.
Use Observable Framework to build data apps locally. Use data loaders to build in any language or library, including Python, SQL, and R.
Seamlessly deploy to Observable. Test before you ship, use automatic deploy-on-commit, and ensure your projects are always up-to-date.