tensorFlow中常见的几种随机函数用法

• tensorFlow中常见的几种随机函数用法
• 参考博客：https://blog.csdn.net/uestc_c2_403/article/details/72810506

# -*- coding: utf-8 -*-
"""
Created on Fri Jun 29 16:12:58 2018

@author: muli
"""

import tensorflow as tf
#tf.random_normal(shape,mean=0.0,stddev=1.0,dtype=tf.float32) 
#tf.truncated_normal(shape, mean=0.0, stddev=1.0, dtype=tf.float32) 
#tf.random_uniform(shape,minval=0,maxval=None,dtype=tf.float32)

#这几个都是用于生成随机数tensor的。尺寸是shape 
#random_normal: 正太分布随机数，均值mean,标准差stddev 
#truncated_normal:截断正态分布随机数，均值mean,标准差stddev,不过只保留[mean-2*stddev,mean+2*stddev]范围内的随机数 
#random_uniform:均匀分布随机数，范围为[minval,maxval]

# 生成2*2的矩阵
x=tf.random_normal((2,2))
y=tf.truncated_normal((2,2))
z=tf.random_uniform((2,2),-1,1)

with tf.Session() as sess:
    print(sess.run(x))
    print("------------------------------------")
    print(sess.run(y))
    print("------------------------------------")
    print(sess.run(z))