Tensorflow.js tf.constraints.nonNeg() Function
Last Updated :
19 Jul, 2022
Tensorflow.js is an open-source library that is being developed by Google for running machine learning models as well as deep learning neural networks in the browser or node environment.
The tf.constraints.nonNeg() function us used to create a nonNeg constraint. nonNeg is a non-negative weight constraint. It is inherited from constraint class. Constraints are the attributes of layers.
Syntax:
tf.constraints.nonNeg()
Parameters:
- w: It specifies the input weight variable. It is an optional parameter.
Return value: It returns tf.constraints.Constraint.
Example 1:
Javascript
import * as tf from "@tensorflow/tfjs"
const constraint = tf.constraints.nonNeg( )
console.log(constraint)
|
Output
{}
Example 2: In this example we will create a dense layer using nonNeg constraint and apply the layer formed to a tensor.
Javascript
import * as tf from "@tensorflow/tfjs"
const constraint = tf.constraints.nonNeg()
const denseLayer = tf.layers.dense({
units: 4,
kernelInitializer: 'heNormal' ,
kernelConstraint: constraint ,
biasConstraint: constraint ,
useBias: true
});
const input = tf.ones([2, 2]);
const output = denseLayer.apply(input);
output.print()
|
Output
Tensor
[[-0.7439224, -1.3572885, -1.2860565, 1.3913929],
[-0.7439224, -1.3572885, -1.2860565, 1.3913929]]
Reference: https://js.tensorflow.org/api/1.0.0/#constraints.nonNeg
Like Article
Suggest improvement
Share your thoughts in the comments
Please Login to comment...