const model = tf.sequential();
model.add(tf.layers.dense({
units: 1,
inputShape: [1]
}));
// Prepare the model for training: Specify the loss and the optimizer.
model.compile({
loss: 'meanSquaredError',
optimizer: 'sgd'
});
// Generate some synthetic data for training.
const xs = tf.tensor2d([1, 2, 3, 4], [4, 1]);
const ys = tf.tensor2d([1, 3, 5, 7], [4, 1]);
console.log(xs,ys)
// Train the model using the data.
model.fit(xs, ys).then(() => {
// Use the model to do inference on a data point the model hasn't seen before:
// Open the browser devtools to see the output
model.predict(tf.tensor2d([5], [1, 1])).print();
});
Please Whitelist JSFiddle in your content blocker.
Help keep JSFiddle free for always by one of two ways:
Whitelist JSFiddle in your content blocker (two clicks)
Go PRO and get access to additional PRO features →
Join the 4+ million users, and keep the JSFiddle dream alive.
Ad-free
All ads in the editor and listing pages are turned completely off.
Use pre-released features
You get to try and use features (like the Palette Color Generator) months before everyone else.
Fiddle collections
Sort and categorize your Fiddles into multiple collections.
Private collections and fiddles
You can make as many Private Fiddles, and Private Collections as you wish!
Console
Debug your Fiddle with a minimal built-in JavaScript console.