TensorFlow中权重的随机初始化

Posted 2020-06-14

　　一开始没看懂stddev是什么参数，找了一下，在tensorflow/python/ops里有random_ops，其中是这么写的：

def random_normal(shape, mean=0.0, stddev=1.0, dtype=types.float32,
                  seed=None, name=None):
  """Outputs random values from a normal distribution.

  Args:
    shape: A 1-D integer Tensor or Python array. The shape of the output tensor.
    mean: A 0-D Tensor or Python value of type `dtype`. The mean of the normal
      distribution.
    stddev: A 0-D Tensor or Python value of type `dtype`. The standard deviation
      of the normal distribution.
    dtype: The type of the output.
    seed: A Python integer. Used to create a random seed for the distribution.
      See
      [`set_random_seed`](../../api_docs/python/constant_op.md#set_random_seed)
      for behavior.
    name: A name for the operation (optional).

  Returns:
    A tensor of the specified shape filled with random normal values.
  """

　　也就是按照正态分布初始化权重，mean是正态分布的平均值，stddev是正态分布的标准差（standard deviation），seed是作为分布的random seed（随机种子，我百度了一下，跟什么伪随机数发生器还有关，就是产生随机数的），在mnist/concolutional中seed赋值为66478，挺有意思，不知道是什么原理。

 

　　后面还有truncated_normal的定义：

def truncated_normal(shape, mean=0.0, stddev=1.0, dtype=types.float32,
                     seed=None, name=None):
  """Outputs random values from a truncated normal distribution.

  The generated values follow a normal distribution with specified mean and
  standard deviation, except that values whose magnitude is more than 2 standard
  deviations from the mean are dropped and re-picked.

  Args:
    shape: A 1-D integer Tensor or Python array. The shape of the output tensor.
    mean: A 0-D Tensor or Python value of type `dtype`. The mean of the
      truncated normal distribution.
    stddev: A 0-D Tensor or Python value of type `dtype`. The standard deviation
      of the truncated normal distribution.
    dtype: The type of the output.
    seed: A Python integer. Used to create a random seed for the distribution.
      See
      [`set_random_seed`](../../api_docs/python/constant_op.md#set_random_seed)
      for behavior.
    name: A name for the operation (optional).

  Returns:
    A tensor of the specified shape filled with random truncated normal values.
  """

　　截断正态分布，以前都没听说过。

 

　　TensorFlow还提供了平均分布等。

 

参考：

1.https://tensorflow.googlesource.com/tensorflow/+/refs/heads/master/tensorflow/g3doc/api_docs/python

2.随机种子：http://baike.baidu.com/link?url=bjDp9u9pkEg2oWOffMep1RW6B1U-0AX2FNmykTtCAa8L_7xzA0ygq6AyLBf8pv7XW8b4gwUKlvMWiCsp32Nu8K