Tensorflow.js tf.randomGamma()函数
Tensorflow.js是谷歌开发的一个开源库,用于在浏览器或节点环境中运行机器学习模型和深度学习神经网络。
tf.randomGamma()函数用于创建一个 tf.Tensor,其值从伽马分布中采样。
句法:
tf.randomGamma(shape, alpha, beta, dtype, seed)
参数:该函数接受三个参数,如下图所示:
- shape:定义输出张量形状的整数数组。
- alpha : 伽马分布的形状参数。
- beta :这是一个可选参数。伽马分布的逆尺度参数。默认值为 1。
- dtype:输出的数据类型。可能的数据类型值是“float32”或“int32”。它也是一个可选参数。
- 种子:这是一个可选参数。随机数生成器的种子。
返回:它返回 tf.Tensor
示例 1:
Javascript
// Importting the tensorflow.js library
import * as tf from "@tensorflow/tfjs"
// Creating the tensor with values sampled
// from a gamma distribution
const x=tf.randomGamma([5], 0);
// Printing the tensor
x.print();
Javascript
// Importting the tensorflow.js library
import * as tf from "@tensorflow/tfjs"
// Creating the tensor with values sampled
// from a gamma distribution
const x=tf.randomGamma([5], 1);
// Printing the tensor
x.print();
Javascript
// Importting the tensorflow.js library
import * as tf from "@tensorflow/tfjs"
// Creating the tensor with values sampled
// from a gamma distribution
const x=tf.randomGamma([2,2], 1);
// Printing the tensor
x.print();
Javascript
// Importting the tensorflow.js library
import * as tf from "@tensorflow/tfjs"
// Creating the tensor with values sampled
// from a gamma distribution
const x=tf.randomGamma([5], 1,2,'int32',98);
// Printing the tensor
x.print();
输出:
Tensor
[0, 0, 0, 0, 0]
示例 2:
Javascript
// Importting the tensorflow.js library
import * as tf from "@tensorflow/tfjs"
// Creating the tensor with values sampled
// from a gamma distribution
const x=tf.randomGamma([5], 1);
// Printing the tensor
x.print();
输出:
Tensor
[1.4808178, 1.6668015, 0.9527208, 1.6024575, 1.6021353]
示例 3:
Javascript
// Importting the tensorflow.js library
import * as tf from "@tensorflow/tfjs"
// Creating the tensor with values sampled
// from a gamma distribution
const x=tf.randomGamma([2,2], 1);
// Printing the tensor
x.print();
输出:
Tensor
[[0.1157758, 1.4427431],
[0.4978852, 0.1617882]]
示例 4:
Javascript
// Importting the tensorflow.js library
import * as tf from "@tensorflow/tfjs"
// Creating the tensor with values sampled
// from a gamma distribution
const x=tf.randomGamma([5], 1,2,'int32',98);
// Printing the tensor
x.print();
输出:
Tensor
[0, 1, 4, 0, 1]
参考: https://js.tensorflow.org/api/latest/#randomGamma