tensorflow变量定义和赋值没有python那么简单，需要在session中run才能拿到结果

``````import tensorflow as tf

w = tf.Variable([[1.0,2.0]])
print(w)#<tf.Variable 'Variable:0' shape=(1, 2) dtype=float32_ref>
x = tf.Variable([[1.0],[0.5]])
print(x)#<tf.Variable 'Variable_1:0' shape=(2, 1) dtype=float32_ref>

y = tf.matmul(w,x)
print(y)#Tensor("MatMul:0", shape=(1, 1), dtype=float32)

#全局变量初始化
init_op = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init_op)
print(y.eval())#[[2.]]
res = sess.run(y)
print(res)#[[2.]]
``````

``````import tensorflow as tf

norm = tf.random_normal([2,3], mean=-1, stddev=4)

var_constant = tf.constant([[1,2,3],[4,5,6]])
shuff = tf.random_shuffle(var_constant)#洗牌

with tf.Session() as sess:
var_norm = sess.run(norm)
var_shuff = sess.run(shuff)
print(var_norm)
print(var_shuff)``````

``````import tensorflow as tf

#累加器
state = tf.Variable(0)
update = tf.assign(state, new_value)

with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for i in range(10):
var_update = sess.run(update)
print(var_update)
``````

``````import tensorflow as tf

var_1 = tf.constant(10.0)
var_2 = tf.constant(5.0)