Tensorflow.js tf.spectral.fft () Function
Last Updated :
10 May, 2021
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.spectral.fft() function is used for FFT(Fast Fourier transform) i.e. it computes the specified 1-dimensional DFT(discrete Fourier transform) over the inner-most dimension of the input.
Syntax:
tf.spectral.fft(input)
Parameters:
- input: The complex input on which an fft is being performed.
Return Value: It returns the result for the computation of the specified 1-dimensional DFT(discrete Fourier transform) over the inner-most dimension of the input.
Example 1:
Javascript
import * as tf from "@tensorflow/tfjs"
const real = tf.tensor1d([1]);
const imag = tf.tensor1d([2]);
const x = tf.complex(real, imag);
tf.spectral.fft(x).print();
|
Output:
Tensor
[1 + 2j]
Example 2:
Javascript
import * as tf from "@tensorflow/tfjs"
const x = tf.complex(tf.tensor1d([1, 3, 5]), tf.tensor1d([2, 4, 6]));
tf.spectral.fft(x).print();
|
Output:
Tensor
[9 + 12j, -4.7320504 + -1.2679477j,
-1.2679505 + -4.7320504j]
Reference: https://js.tensorflow.org/api/latest/#spectral.fft
Share your thoughts in the comments
Please Login to comment...