Tensorflow.js tf.initializers.Initializer Class

9 August 2024

0

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.initializers.Initializer() class is used to extend serialization.Serializable class. It is the base class of Initializer.

This tf.initializers.Initializer class contains fifteen inbuilt functions which are illustrated below:

tf.initializers.Initializer class .constant() function
tf.initializers.Initializer class .glorotNormal() function
tf.initializers.Initializer class .glorotUniform() function
tf.initializers.Initializer class .heNormal() function
tf.initializers.Initializer class .heUniform() function
tf.initializers.Initializer class .identity() function
tf.initializers.Initializer class .leCunNormal() function
tf.initializers.Initializer class .leCunUniform() function
tf.initializers.Initializer class .ones() function
tf.initializers.Initializer class .orthogonal() function
tf.initializers.Initializer class .randomNormal() function
tf.initializers.Initializer class .randomUniform() function
tf.initializers.Initializer class .truncatedNormal() function
tf.initializers.Initializer class .varianceScaling() function
tf.initializers.Initializer class .zeros() function

1. tf.initializers.Initializer class .constant() function: It is used to generate the values initialized to some constant.

Example:

Javascript

// Importing the tensorflow.js library
const tf = require("@tensorflow/tfjs")
 
// Use tf.initializers.constant() function
var initializer = tf.initializers.constant({ value: 7, })
 
// Print the value of constant
console.log(initializer);

Output:

Constant { value: 7 }

2. tf.initializers.Initializer class .glorotNormal() function: It extract samples from a truncated normal distribution which is been centered at 0 with stddev = sqrt(2 / (fan_in + fan_out)). Note, that the fan_in is the number of inputs in the tensor weight and the fan_out is the number of outputs in the tensor weight.

Example:

Javascript

// Importing the tensorflow.js library
import * as tf from "@tensorflow/tfjs"
 
// Initializing the .initializers.glorotNormal() function
console.log(tf.initializers.glorotNormal(9));
 
// Printing Individual gainvalues
console.log('\nIndividual values:\n');
console.log(tf.initializers.glorotNormal(9).scale);
console.log(tf.initializers.glorotNormal(9).mode);
console.log(tf.initializers.glorotNormal(9).distribution);

Output:

{
    "scale": 1,
    "mode": "fanAvg",
    "distribution": "normal"
}

Individual values:

1
fanAvg
normal

3. tf.initializers.Initializer class .glorotUniform() function: It is used to extract samples from a uniform distribution within [-limit, limit] where limit is sqrt(6 / (fan_in + fan_out)) where fan_in is the number of input units in the weight tensor and fan out is the number of output units in the weight tensor.

Example:

Javascript

// Importing the tensorflow.Js library
import * as tf from "@tensorflow/tfjs"
 
// Initializing the .initializers.glorotUniform() function
const geek = tf.initializers.glorotUniform(7)
 
// Printing gain value
console.log(geek);
 
// Printing individual values from gain
console.log('\nIndividual values:\n');
console.log(geek.scale);
console.log(geek.mode);
console.log(geek.distribution);

Output:

{
  "scale": 1,
  "mode": "fanAvg",
  "distribution": "uniform"
}

Individual values:

1
fanAvg
uniform

4. tf.initializers.Initializer class .heNormal() function: It is used to draw samples from a truncated normal distribution centered on zero with stddev = sqrt(2 / fanIn) within [-limit, limit] where, limit is sqrt(6 / fan_in). Note, that the fanIn is the number of inputs in the tensor weight.

Example:

Javascript

// Importing the tensorflow.js library
import * as tf from "@tensorflow/tfjs"
 
// Initializing the .initializers.heNormal()
// function
const geek = tf.initializers.heNormal(7)
 
// Printing gain
console.log(geek);
console.log('\nIndividual values:\n');
console.log(geek.scale);
console.log(geek.mode);
console.log(geek.distribution);

Output:

{
  "scale": 2,
  "mode": "fanIn",
  "distribution": "normal"
}

Individual values:

2
fanIn
normal

5. tf.initializers.Initializer class .heUniform() function: It draws samples from a uniform distribution within [-cap, cap] where, cap is sqrt(6 / fan_in). Note, that the fanIn is the number of inputs in the tensor weight.

Example:

Javascript

// Importing the tensorflow.js library
import * as tf from "@tensorflow/tfjs"
 
// Initializing the .initializers.heUniform() function
const geek = tf.initializers.heUniform(7)
 
// Printing gain
console.log(geek);
console.log('\nIndividual values:\n');
console.log(geek.scale);
console.log(geek.mode);
console.log(geek.distribution);

Output:

{
    "scale": 2,
    "mode": "fanIn",
    "distribution": "uniform"
}

Individual values:

2
fanIn
uniform

6. tf.initializers.Initializer class .identity() function: It is used to return a new tensor object with an identity matrix. Its only used for 2D matrices.

Example:

Javascript

// Importing the tensorflow.Js library
import * as tf from "@tensorflow/tfjs"
 
// Generates the identity matrix
const value=tf.initializers.identity(1.0)
 
// Print gain
console.log(value)

Output:

{
 "gain": 1
}

7. tf.initializers.Initializer class .leCunNormal() function: It is used to extract samples from a truncated normal distribution which is centered at zero with stddev = sqrt(1 / fanIn). Note, that fanIn is the number of inputs in the tensor weight.

Example:

Javascript

// Importing the tensorflow.Js library
import * as tf from "@tensorflow/tfjs"
 
// Initializing the .initializers.leCunNormal() function
const geek = tf.initializers.leCunNormal(3)
 
// Printing gain
console.log(geek);
console.log('\nIndividual values:\n');
console.log(geek.scale);
console.log(geek.mode);
console.log(geek.distribution);

Output:

{
    "scale": 1,
    "mode": "fanIn",
    "distribution": "normal"
}

Individual values:

1
fanIn
normal

8. tf.initializers.Initializer class .leCunUniform() function: It takes samples from a uniform distribution in the interval [-cap, cap] with cap = sqrt(3 / fanIn). Note, that fanIn is the number of inputs in the tensor weight.

Example:

Javascript

// Importing the tensorflow.Js library
import * as tf from "@tensorflow/tfjs"
 
// Initialising the .initializers.leCunUniform() function
console.log(tf.initializers.leCunUniform(4));
 
// Printing individual values from the gain
console.log("\nIndividual Values\n");
console.log(tf.initializers.leCunUniform(4).scale);
console.log(tf.initializers.leCunUniform(4).mode);
console.log(tf.initializers.leCunUniform(4).distribution);

Output:

{
  "scale": 1,
  "mode": "fanIn",
  "distribution": "uniform"
}

Individual Values

1
fanIn
uniform

9. tf.initializers.Initializer class .ones() function: It is used to create a tensor with all elements set to 1, or it initializes tensor with value 1.

Example:

Javascript

//import tensorflow.js
const tf=require("@tensorflow/tfjs")
 
//use tf.ones()
var GFG=tf.ones([3, 4]);
 
//print tensor
GFG.print()

Output:

Tensor
   [[1, 1, 1, 1],
    [1, 1, 1, 1],
    [1, 1, 1, 1]]

10. tf.initializers.Initializer class .orthogonal() function: It produces a random orthogonal matrix.

Example:

Javascript

// Importing the tensorflow.js library
import * as tf from "@tensorflow/tfjs"
 
// Initializing the .initializers.orthogonal() function
let geek = tf.initializers.orthogonal(2)
 
// Printing gain value
console.log(geek);
 
// Printing individual gain value
console.log('\nIndividual values:\n');
console.log(geek.DEFAULT_GAIN);
console.log(geek.gain);

Output:

{
  "DEFAULT_GAIN": 1,
  "gain": 1
}

Individual values:

1
1

11. tf.initializers.Initializer class .randomNormal() function: It is used to produce random values that are initialized to a normal distribution.

Example:

Javascript

// Importing the tensorflow.js library
import * as tf from "@tensorflow/tfjs"
 
// Initializing the .initializers.randomNormal() function
let geek = tf.initializers.randomNormal(3)
 
// Printing gain value
console.log(geek);
 
// Printing individual gain value.
console.log('\nIndividual values:\n');
console.log(geek.DEFAULT_MEAN);
console.log(geek.DEFAULT_STDDEV);
console.log(geek.mean);
console.log(geek.stddev);

Output:

{
  "DEFAULT_MEAN": 0,
  "DEFAULT_STDDEV": 0.05,
  "mean": 0,
  "stddev": 0.05
}

Individual values:

0
0.05
0
0.05

12. tf.initializers.Initializer class .randomUniform() function: It is used to generate random values that are initialized to a uniform distribution. The values are distributed uniformly between the configured min-value and max-value.

Example:

Javascript

// Importing the tensorflow.js library
import * as tf from "@tensorflow/tfjs"
 
// Initializing the .initializers.randomUniform() function
let geek = tf.initializers.randomUniform(5)
 
// Printing gain value
console.log(geek);
 
// Printing individual gain value.
console.log('\nIndividual values:\n');
console.log(geek.DEFAULT_MINVAL);
console.log(geek.DEFAULT_MAXVAL);
console.log(geek.minval);
console.log(geek.maxval);

Output:

{
  "DEFAULT_MINVAL": -0.05,
  "DEFAULT_MAXVAL": 0.05,
  "minval": -0.05,
  "maxval": 0.05
}

Individual values:

-0.05
0.05
-0.05
0.05

13. tf.initializers.Initializer class .truncatedNormal(): It function produces random values initialized to a truncated normal distribution.

Example:

Javascript

// Importing the tensorflow.js library
import * as tf from "@tensorflow/tfjs"
 
// Initializing the .initializers.truncatedNormal()
// function
let geek = tf.initializers.truncatedNormal(13)
 
// Printing gain value
console.log(geek);
 
// Printing individual gain value
console.log('\nIndividual values:\n');
console.log(geek.DEFAULT_MEAN);
console.log(geek.DEFAULT_STDDEV);
console.log(geek.mean);
console.log(geek.stddev);

Output:

{
  "DEFAULT_MEAN": 0,
  "DEFAULT_STDDEV": 0.05,
  "mean": 0,
  "stddev": 0.05
}

Individual values:

0
0.05
0
0.05

14. tf.initializers.Initializer class .varianceScaling() function: It is capable of adjusting its scale to the shape of weights. Using the value of distribution = NORMAL, samples are drawn from a truncated normal distribution that has center at 0, with stddev = sqrt(scale / n).

Example:

Javascript

// Importing the tensorflow.js library
import * as tf from "@tensorflow/tfjs"
 
// Initializing the .initializers.varianceScaling()
// function
let geek = tf.initializers.varianceScaling(33)
 
// Printing gain value
console.log(geek);
 
// Printing individual gain value.
console.log('\nIndividual values:\n');
console.log(geek.scale);
console.log(geek.mode);
console.log(geek.distribution);

Output:

{
  "scale": 1,
  "mode": "fanIn",
  "distribution": "normal"
}

Individual values:

1
fanIn
normal

15. tf.initializers.Initializer class .zeros() function: It is an initializer that is used to produce tensors that are initialized to zero.

Example:

Javascript

// Importing the tensorflow.Js library
import * as tf from "@tensorflow/tfjs"
 
// Calling tf.initializers.zeros() function
const initializer = tf.initializers.zeros();
 
// Printing output
console.log(JSON.stringify(+initializer));

Output:

null

Reference: https://js.tensorflow.org/api/latest/#class:initializers.Initializer

Whether you’re preparing for your first job interview or aiming to upskill in this ever-evolving tech landscape, neveropen Courses are your key to success. We provide top-quality content at affordable prices, all geared towards accelerating your growth in a time-bound manner. Join the millions we’ve already empowered, and we’re here to do the same for you. Don’t miss out – check it out now!

Tensorflow.js tf.initializers.Initializer Class

Javascript

Javascript

Javascript

Javascript

Javascript

Javascript

Javascript

Javascript

Javascript

Javascript

Javascript

Javascript

Javascript

Javascript

Javascript

Java Program for Longest Common Subsequence

Maximum height of Tree when any Node can be considered as Root

Print Fibonacci sequence using 2 variables

LEAVE A REPLY Cancel reply

Most Popular

5 Best Antiviruses With Keylogger Protection in 2025 by Tyler Cross

Best VPNs for School in 2025 That Work With Firewalls by Toma Novakovic

How to Watch the Super Bowl From Anywhere in 2025 by Raven Wu

Best Malware Removal + Protection Software in 2025 by Raven Wu

Recent Comments

EDITOR PICKS

5 Best Antiviruses With Keylogger Protection in 2025 by Tyler Cross

Best VPNs for School in 2025 That Work With Firewalls by Toma Novakovic

How to Watch the Super Bowl From Anywhere in 2025 by Raven Wu

POPULAR POSTS

5 Best Antiviruses With Keylogger Protection in 2025 by Tyler Cross

Best VPNs for School in 2025 That Work With Firewalls by Toma Novakovic

How to Watch the Super Bowl From Anywhere in 2025 by Raven Wu

POPULAR CATEGORY

ABOUT US

FOLLOW US