Method initialized_value

tensorflow/python/ops/variables.py:724–748

Returns the value of the initialized variable. You should use this instead of the variable itself to initialize another variable with a value that depends on the value of this variable. ```python # Initialize 'v' with a random tensor. v = tf.Variable(tf.random.truncated_normal(

(self)

      None, "Use Variable.read_value. Variables in 2.X are initialized "
      "automatically both in eager and graph (inside tf.defun) contexts.")
  def initialized_value(self):
    """Returns the value of the initialized variable.

    You should use this instead of the variable itself to initialize another
    variable with a value that depends on the value of this variable.

    ```python
    # Initialize 'v' with a random tensor.
    v = tf.Variable(tf.random.truncated_normal([10, 40]))
    # Use `initialized_value` to guarantee that `v` has been
    # initialized before its value is used to initialize `w`.
    # The random values are picked only once.
    w = tf.Variable(v.initialized_value() * 2.0)
    ```

    Returns:
      A `Tensor` holding the value of this variable after its initializer
      has run.
    """
    with ops.init_scope():
      # optimize node placement policy in initialized_value stage.
      with ops.colocate_with(self):
        return control_flow_ops.cond(is_variable_initialized(self),
                                     self.read_value,
                                     lambda: self.initial_value)

  @property
  def initial_value(self):