tf.test.compute_gradient

View source on GitHub

Computes the theoretical and numeric Jacobian of f.

tf.test.compute_gradient(
    f, x, delta=0.001
)

With y = f(x), computes the theoretical and numeric Jacobian dy/dx.

Args
f	the function.
x	the arguments for the function as a list or tuple of values convertible to a Tensor.
delta	(optional) perturbation used to compute numeric Jacobian.

Returns
A pair of lists, where the first is a list of 2-d numpy arrays representing the theoretical Jacobians for each argument, and the second list is the numerical ones. Each 2-d array has "y_size" rows and "x_size" columns where "x_size" is the number of elements in the corresponding argument and "y_size" is the number of elements in f(x).

Raises
ValueError	If result is empty but the gradient is nonzero.
ValueError	If x is not list, but any other type.

Example:

@tf.function
def test_func(x):
  return x*x

theoretical, numerical = tf.test.compute_gradient(test_func, [1.0])
theoretical, numerical
# ((array([[2.]], dtype=float32),), (array([[2.000004]], dtype=float32),))