def test_diffs(self):
x = tf.constant([1, 2, 3, 4, 5])
dx = self.evaluate(math.diff(x, order=1, exclusive=False))
np.testing.assert_array_equal(dx, [1, 1, 1, 1, 1])
dx1 = self.evaluate(math.diff(x, order=1, exclusive=True))
np.testing.assert_array_equal(dx1, [1, 1, 1, 1])
dx2 = self.evaluate(math.diff(x, order=2, exclusive=False))
np.testing.assert_array_equal(dx2, [1, 2, 2, 2, 2])
def test_diffs_differentiable(self):
"""Tests that the diffs op is differentiable."""
x = tf.constant(2.0)
xv = tf.stack([x, x * x, x * x * x], axis=0)
# Produces [x, x^2 - x, x^3 - x^2]
dxv = self.evaluate(math.diff(xv))
np.testing.assert_array_equal(dxv, [2., 2., 4.])
grad = self.evaluate(tf.gradients(math.diff(xv), x)[0])
# Note that TF gradients adds up the components of the jacobian.
# The sum of [1, 2x-1, 3x^2-2x] at x = 2 is 12.
self.assertEqual(grad, 12.0)
def test_batched_axis(self, exclusive, axis, dx_true):
"""Tests batch diff works with axis argument use of exclusivity."""
x = tf.constant([[1, 2, 3, 4], [10, 20, 30, 40]])
dx = self.evaluate(
math.diff(x, order=1, exclusive=exclusive, axis=axis))
self.assertAllEqual(dx, dx_true)
def test_batch_diff(self):
"""Tests that the diffs op works on batched inputs."""
x = tf.constant([[1, 2, 3, 4], [10, 20, 30, 40]])
dx_true = np.array([[1, 1, 1], [10, 10, 10]])
dx = self.evaluate(math.diff(x, order=1, exclusive=True))
self.assertAllEqual(dx, dx_true)