Regression Lineaire
Introduction
show(tf.scalar(1));
show(tf.tensor1d([0, 1, 2, 3]));
show(tf.tensor2d([[0, 0], [1, 1]]));
show(tf.tensor([[0], [1], [2]], shape));
shape = [3, 1];
show(tf.tensor([[0], [1], [2]]));
Type JavaScript, then Shift-Enter. Ctrl-space for more options. Arrow ↑/↓ to switch modes.
{
const initial = tf.zeros([3]);
let variable = tf.variable(initial);
variable.print(); // affiche [0, 0, 0]
const updated = tf.tensor1d([1, 1, 1]);
variable.assign(updated);
return show(variable);
}
{
const a = tf.tensor2d([[10, 20], [30, 40]]);
const b = tf.tensor2d([[50, 60], [70, 80]]);
const c = a.add(b);
return show(c);
}
show(tf.tensor1d([11, 22, 33, 44]).square());
{
const a = tf.tensor3d([[[5, 20], [10, 40], [30, 75]]]);
const b = tf.tensor3d([[[50, 60], [70, 80], [115, 160]]]);
const c = a.mul(b).square().sub(tf.scalar(1000));
return show(c);
}
{
const x = tf.tensor2d([[0.0, 2.0], [4.0, 6.0]]);
x.dispose();
return show(x);
}
{
const average = tf.tidy(() => {
const y = tf.tensor1d([1.0, 2.0, 3.0, 4.0]);
const z = tf.ones([4]);
return y.sub(z).square().mean();
});
return show(average);
}
tf = require('@tensorflow/tfjs');
import {show} from '@zaidalyafeai/show-tensor'
Purpose-built for displays of data
Observable is your go-to platform for exploring data and creating expressive data visualizations. Use reactive JavaScript notebooks for prototyping and a collaborative canvas for visual data exploration and dashboard creation.
