tf.truncated_normal

tf.truncated_normal(shape, mean=0.0, stddev=1.0, dtype=tf.float32, seed=None, name=None)

 从截断的正态分布中输出随机值，产生正太分布的值如果与均值的差值大于两倍的标准差，那就重新生成。

shape表示生成张量的维度；

mean是均值；

stddev是标准差。

 

# -*- coding: utf-8 -*-
import tensorflow as tf
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D


def plt3D(data):
    X = []
    Y = []
    Z = []
    for i in range(len(data)):
        for j in range(len(data[i])):
            X.append(i)
            Y.append(j)
            Z.append(data[i][j])
    fig = plt.figure()
    ax = fig.add_subplot(111, projection='3d')
    ax.scatter(X, Y, Z, c='r', marker='o')
    ax.set_xlabel('x')
    ax.set_ylabel('y')
    ax.set_zlabel('z')
    plt.show()

if __name__ == "__main__":
    c = tf.truncated_normal(shape=[10, 10], mean=0, stddev=1)
    with tf.Session() as sess:
        data = sess.run(c)
        plt3D(data)