Open In App

Tensorflow.js tf.linalg.gramSchmidt() Function

Improve
Improve
Like Article
Like
Save
Share
Report

Tensorflow.js is an open-source library developed by Google for running machine learning models and deep learning neural networks in the browser or node environment.

The tf.linalg.gramSchmidt() function is used to orthogonalize the vectors using the Gram-Schimdt process.

Syntax:

tf.linalg.gramSchmidt( xs ) 

Parameters:

  • xs ( a tf.Tensor1D array or tf.Tensor2D): These are the vectors that are to be orthogonalized.

Return Value: It returns a tf.Tensor1D array or tf.Tensor2D.

Example 1:

Javascript




const tf = require("@tensorflow/tfjs")
  
// Creating a 2-D tensor
const input = tf.tensor2d([
    [3, 7], 
    [4, 6]
]);
  
// Getting the orthogonalized vector
let result = tf.linalg.gramSchmidt(input);
  
result.print();


Output:

Tensor
    [[0.3939193, 0.919145  ],
     [0.919145 , -0.3939194]]

Example 2:

Javascript




const tf = require("@tensorflow/tfjs")
  
// Creating a 2-D tensor
const input = tf.tensor2d([
    [5, 7, 2], 
    [7, 6, 9],
    [1, 2, 3]
]);
  
// Getting the orthogonalized vector
let result = tf.linalg.gramSchmidt(input);
  
result.print();


Output:

Tensor
    [[0.5661386, 0.792594  , 0.2264554],
     [0.1283516, -0.3561312, 0.925579 ],
     [-0.814256, 0.4949402 , 0.3033505]]

Reference: https://js.tensorflow.org/api/latest/#linalg.gramSchmidt


Last Updated : 02 Jun, 2021
Like Article
Save Article
Previous
Next
Share your thoughts in the comments
Similar Reads