变量的初始化方法

tf.get_variable的初始化调用为：
tf.get_variable(name, shape=None, initializer=None, dtype=tf.float32, trainable=True, collections=None)

变量初始化的方法

tf.constant_initializer(const)：常量初始化函数
tf.random_normal_initializer()：正态分布初始化函数
tf.truncated_normal_initializer(mean = 0.0, stddev = 1.0, seed = None, dtype = dtypes.float32)：截取的正态分布初始化函数
tf.random_uniform_initializer(minval = 0, maxval = None, seed = None, dtype = dtypes.float32)：均匀分布初始化函数
tf.zeros_initializer()：全0常量初始化函数
tf.ones_initializer()：全1常量初始化函数
tf.uniform_unit_scaling_initializer(factor = 1.0, seed = None, dtype = dtypes.float32)：均匀分布（不指定最小、最大值），初始化函数
tf.variance_scaling_initializer(scale = 1.0, mode = "fan_in", distribution = "normal", seed = None, dtype = dtypes.float32)：由mode确定是截取的正态分布，还是均匀分布初始化函数
tf.orthogonal_initializer()：正交矩阵初始化函数
tf.glorot_uniform_initializer()：由输入单元节点数和输出单元节点数确定的均匀分布初始化函数
tf.glorot_normal_initializer()：由输入单元节点数和输出单元节点数确定的截取的正态分布初始化函数

基本的变量初始化为：

tf.ones(shape, dtype = tf.float32, name = None)
tf.zeros(shape, dtype = tf.float32, name = None)
tf.ones_like(tensor, dtype = None, name = None)
tf.zeros_like(tensor, dtype = None, name = None)
tf.fill([dim](https://www.baidu.com/s?wd=dim&tn=24004469_oem_dg&rsv_dl=gh_pl_sl_csd), value, name = None)
tf.constant(value, dtype = None, shape = None, name = None)
tf.linspace(start, stop, num, name = None)
tf.range(start, limit = None, delta = 1, name = None)
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, maxval = None, dtype = tf.float32, seed = None, name = None)
tf.random_shuffle(value, seed =None, name = None)
tf.set_random_seed(seed)：设置产生随机数的种子