Method compute_gradients

tensorflow/python/training/optimizer.py:478–593

Compute gradients of `loss` for the variables in `var_list`. This is the first part of `minimize()`. It returns a list of (gradient, variable) pairs where "gradient" is the gradient for "variable". Note that "gradient" can be a `Tensor`, an `IndexedSlices`, or `None` if there is n

(self, loss, var_list=None,
                        gate_gradients=GATE_OP,
                        aggregation_method=None,
                        colocate_gradients_with_ops=False,
                        grad_loss=None)

                                name=name)

  def compute_gradients(self, loss, var_list=None,
                        gate_gradients=GATE_OP,
                        aggregation_method=None,
                        colocate_gradients_with_ops=False,
                        grad_loss=None):
    """Compute gradients of `loss` for the variables in `var_list`.

    This is the first part of `minimize()`.  It returns a list
    of (gradient, variable) pairs where "gradient" is the gradient
    for "variable".  Note that "gradient" can be a `Tensor`, an
    `IndexedSlices`, or `None` if there is no gradient for the
    given variable.

    Args:
      loss: A Tensor containing the value to minimize or a callable taking
        no arguments which returns the value to minimize. When eager execution
        is enabled it must be a callable.
      var_list: Optional list or tuple of `tf.Variable` to update to minimize
        `loss`.  Defaults to the list of variables collected in the graph
        under the key `GraphKeys.TRAINABLE_VARIABLES`.
      gate_gradients: How to gate the computation of gradients.  Can be
        `GATE_NONE`, `GATE_OP`, or `GATE_GRAPH`.
      aggregation_method: Specifies the method used to combine gradient terms.
        Valid values are defined in the class `AggregationMethod`.
      colocate_gradients_with_ops: If True, try colocating gradients with
        the corresponding op.
      grad_loss: Optional. A `Tensor` holding the gradient computed for `loss`.

    Returns:
      A list of (gradient, variable) pairs. Variable is always present, but
      gradient can be `None`.

    Raises:
      TypeError: If `var_list` contains anything else than `Variable` objects.
      ValueError: If some arguments are invalid.
      RuntimeError: If called with eager execution enabled and `loss` is
        not callable.

    @compatibility(eager)
    When eager execution is enabled, `gate_gradients`, `aggregation_method`,
    and `colocate_gradients_with_ops` are ignored.
    @end_compatibility
    """
    if self.doing_loss_scaling():
      loss_scale = self._loss_scale()
      if callable(loss):
        loss = lambda: loss() * loss_scale
      else:
        loss = loss * loss_scale

    if callable(loss):
      with backprop.GradientTape() as tape:
        if var_list is not None:
          tape.watch(var_list)
        loss_value = loss()

        # Scale loss if using a "mean" loss reduction and multiple replicas.
        # Have to be careful to call distribute_lib.get_loss_reduction()