TensorFlow学习笔记(18)random_ops.ran

随机正态分布

tf.random.normal(
    shape,
    mean=0.0,
    stddev=1.0,
    dtype=tf.float32,
    seed=None,
    name=None
)

• shape: A 1-D integer Tensor or Python array. The shape of the output tensor.
  输出张量的形状，必选
• mean: A 0-D Tensor or Python value of type dtype. The mean of the normal distribution.
  正态分布的均值，默认为0
• stddev: A 0-D Tensor or Python value of type dtype. The standard deviation of the normal distribution.
  正态分布的标准差，默认为1.0
• dtype: The type of the output.
• seed: A Python integer. Used to create a random seed for the distribution. See tf.set_random_seed for behavior.
• name: A name for the operation (optional).