Method jacobian

tensorflow/python/eager/backprop.py:1023–1125

Computes the jacobian using operations recorded in context of this tape. See [wikipedia article](http://en.wikipedia.org/wiki/jacobian_matrix_and_determinant) for the definition of a Jacobian. Example usage: ```python with tf.GradientTape() as g: x = tf.constant([1.0, 2

(self,
               target,
               sources,
               unconnected_gradients=UnconnectedGradients.NONE,
               parallel_iterations=None,
               experimental_use_pfor=True)

    return grad

  def jacobian(self,
               target,
               sources,
               unconnected_gradients=UnconnectedGradients.NONE,
               parallel_iterations=None,
               experimental_use_pfor=True):
    """Computes the jacobian using operations recorded in context of this tape.

    See [wikipedia article](http://en.wikipedia.org/wiki/jacobian_matrix_and_determinant) for the
    definition of a Jacobian.

    Example usage:

    ```python
    with tf.GradientTape() as g:
      x  = tf.constant([1.0, 2.0])
      g.watch(x)
      y = x * x
    jacobian = g.jacobian(y, x)
    # jacobian value is [[2., 0.], [0., 4.]]
    ```

    Args:
      target: Tensor to be differentiated.
      sources: a list or nested structure of Tensors or Variables. `target`
        will be differentiated against elements in `sources`.
      unconnected_gradients: a value which can either hold 'none' or 'zero' and
        alters the value which will be returned if the target and sources are
        unconnected. The possible values and effects are detailed in
        'UnconnectedGradients' and it defaults to 'none'.
      parallel_iterations: A knob to control how many iterations are dispatched
        in parallel. This knob can be used to control the total memory usage.
      experimental_use_pfor: If true, vectorizes the jacobian computation. Else
        falls back to a sequential while_loop. Vectorization can sometimes fail
        or lead to excessive memory usage. This option can be used to disable
        vectorization in such cases.

    Returns:
      A list or nested structure of Tensors (or None), one for each element in
      `sources`. Returned structure is the same as the structure of `sources`.
      Note if any gradient is sparse (IndexedSlices), jacobian function
      currently makes it dense and returns a Tensor instead. This may change in
      the future.


    Raises:
      RuntimeError: If called on a non-persistent tape with eager execution
        enabled and without enabling experimental_use_pfor.
      ValueError: If vectorization of jacobian computation fails.
    """
    flat_sources = nest.flatten(sources)
    target_static_shape = target.shape
    target_shape = array_ops.shape(target)
    # Note that we push and pop the tape here and below. This is needed since we
    # need gradients through the enclosed operations.
    self._push_tape()
    target = array_ops.reshape(target, [-1])
    self._pop_tape()