原文链接：blog.csdn.net/phdat101/article/details/52442738
正常情况下，使用tf.initialize_all_variables()初始化变量，在完全构建好模型并加载之后才运行这个操作。生成数据的主要方法如下
1）如果需要利用已经初始化的参数给其他变量赋值
TF的变量有个initialized_value()属性，就是初始化的值，使用方法如下：
[python]view plaincopy
# 原始的变量
weights = tf.Variable(tf.random_normal([784,200], stddev=0.35),name="weights")
# 创造相同内容的变量
w2 = tf.Variable(weights.initialized_value(), name="w2")
# 也可以直接乘以比例
w_twice = tf.Variable(weights.initialized_value() *0.2, name="w_twice")
2）生成tensor的一些方法
生成tensor：
tf.zeros(shape, dtype=tf.float32, name=None)
tf.zeros_like(tensor, dtype=None, name=None)
tf.constant(value, dtype=None, shape=None, name='Const')
tf.fill(dims, value, name=None)
tf.ones_like(tensor, dtype=None, name=None)
tf.ones(shape, dtype=tf.float32, name=None)
生成序列
tf.range(start, limit, delta=1, name='range')
tf.linspace(start, stop, num, name=None)
生成随机数
tf.random_normal(shape, mean=0.0, stddev=1.0, dtype=tf.float32, seed=None, name=None)
tf.truncated_normal(shape, mean=0.0, stddev=1.0, dtype=tf.float32, seed=None, name=None)
tf.random_uniform(shape, minval=0.0, maxval=1.0, dtype=tf.float32, seed=None, name=None)
tf.random_shuffle(value, seed=None, name=None)
效果程序：
[python]view plaincopy
importtensorflow as tf
importnumpy as np
# 生成0和1矩阵
v1 = tf.Variable(tf.zeros([3,3,3]), name="v1")
v2 = tf.Variable(tf.ones([10,5]), name="v2")
#填充单值矩阵
v3 = tf.Variable(tf.fill([2,3],9))
#常量矩阵
v4_1 = tf.constant([1,2,3,4,5,6,7])
v4_2 = tf.constant(-1.0, shape=[2,3])
#生成等差数列
v6_1 = tf.linspace(10.0,12.0,30, name="linspace")#float32 or float64
v7_1 = tf.range(10,20,3)#just int32
#生成各种随机数据矩阵
v8_1 = tf.Variable(tf.random_uniform([2,4], minval=0.0, maxval=2.0, dtype=tf.float32, seed=1234, name="v8_1"))
v8_2 = tf.Variable(tf.random_normal([2,3], mean=0.0, stddev=1.0, dtype=tf.float32, seed=1234, name="v8_2"))
v8_3 = tf.Variable(tf.truncated_normal([2,3], mean=0.0, stddev=1.0, dtype=tf.float32, seed=1234, name="v8_3"))
v8_4 = tf.Variable(tf.random_uniform([2,3], minval=0.0, maxval=1.0, dtype=tf.float32, seed=1234, name="v8_4"))
v8_5 = tf.random_shuffle([[1,2,3],[4,5,6],[6,6,6]], seed=134, name="v8_5")
# 初始化
init_op = tf.initialize_all_variables()
# 保存变量，也可以指定保存的内容
saver = tf.train.Saver()
#saver = tf.train.Saver({"my_v2": v2})
#运行
with tf.Session() as sess:
sess.run(init_op)
# 输出形状和值
printtf.Variable.get_shape(v1)#shape
printsess.run(v1)#vaule
# numpy保存文件
np.save("v1.npy",sess.run(v1))#numpy save v1 as file
test_a = np.load("v1.npy")
printtest_a[1,2]
#一些输出
printsess.run(v3)
v5 = tf.zeros_like(sess.run(v1))
printsess.run(v6_1)
printsess.run(v7_1)
printsess.run(v8_5)
#保存图的变量
save_path = saver.save(sess,"/tmp/model.ckpt")
#加载图的变量
#saver.restore(sess, "/tmp/model.ckpt")
print"Model saved in file: ", save_path
