tf.get_variable(name, shape, initializer): name就是变量的名称，shape是变量的维度，initializer是变量初始化的方式，初始化的方式有以下几种：
tf.constant_initializer：常量初始化函数
tf.random_normal_initializer：正态分布
tf.truncated_normal_initializer：截取的正态分布
tf.random_uniform_initializer：均匀分布
tf.zeros_initializer：全部是0
tf.ones_initializer：全是1
tf.uniform_unit_scaling_initializer：满足均匀分布，但不影响输出数量级的随机值
如下应用：
def variable_on_cpu(name, shape, initializer = tf.constant_initializer(0.1)):
with tf.device('/cpu:0'):
dtype = tf.float32
var = tf.get_variable(name, shape, initializer = initializer,
dtype = dtype)
return var
# 用 get_variable 在 CPU 上定义变量
def variables(name, shape, stddev):
dtype = tf.float32
var = variable_on_cpu(name, shape,
tf.truncated_normal_initializer(stddev = stddev,
dtype = dtype))
return var
a1 = tf.get_variable(name='a1', shape=[2,3], initializer=tf.random_normal_initializer(mean=0, stddev=1))
a2 = tf.get_variable(name='a2', shape=[1], initializer=tf.constant_initializer(1))
a3 = tf.get_variable(name='a3', shape=[2,3], initializer=tf.ones_initializer())
a4 = tf.get_variable(name="a4", shape=[3,4], initializer = tf.zeros_initializer())
a5 = variable_on_cpu("a5", shape=[2,4], initializer=tf.ones_initializer())
with tf.Session() as sess:
sess.run(tf.initialize_all_variables())
print(sess.run(a1))
print(sess.run(a2))
print(sess.run(a3))
print(sess.run(a4))
print(sess.run(a5))