def testInvalidShapeAtEval(self):
with self.test_session(use_gpu=self._use_gpu):
v = tf.placeholder(dtype=tf.float32)
with self.assertRaisesOpError("input must be at least 2-dim"):
tf.batch_matrix_set_diag(v, [v]).eval(feed_dict={v: 0.0})
with self.assertRaisesOpError(
r"but received input shape: \[1,1\] and diagonal shape: \[\]"):
tf.batch_matrix_set_diag([[v]], v).eval(feed_dict={v: 0.0})
def testInvalidShapeAtEval(self):
with self.test_session(use_gpu=self._use_gpu):
v = tf.placeholder(dtype=tf.float32)
with self.assertRaisesOpError("input must be at least 2-dim"):
tf.batch_matrix_set_diag(v, [v]).eval(feed_dict={v: 0.0})
with self.assertRaisesOpError(
r"but received input shape: \[1,1\] and diagonal shape: \[\]"):
tf.batch_matrix_set_diag([[v]], v).eval(feed_dict={v: 0.0})
def testVector(self):
with self.test_session(use_gpu=self._use_gpu):
v = np.array([1.0, 2.0, 3.0])
mat = np.array([[0.0, 1.0, 0.0], [1.0, 0.0, 1.0], [1.0, 1.0, 1.0]])
mat_set_diag = np.array([[1.0, 1.0, 0.0], [1.0, 2.0, 1.0],
[1.0, 1.0, 3.0]])
output = tf.batch_matrix_set_diag(mat, v)
self.assertEqual((3, 3), output.get_shape())
self.assertAllEqual(mat_set_diag, output.eval())
def offdiagonal_constrain(var, scope=None):
"""Constrain all offdiagonal values to be positive for variable `var`"""
if tf.get_variable_scope().reuse: return
with tf.name_scope(scope or 'offdiagonal_constrain'):
diag = tf.diag_part(var)
constrained_value = tf.where(tf.greater_equal(var, 0.0), var,
tf.zeros_like(var))
constrained_value = tf.batch_matrix_set_diag(constrained_value, diag)
update = tf.assign(var, constrained_value)
tf.add_to_collection('constraints', update)
return update
def testVector(self):
with self.test_session(use_gpu=self._use_gpu):
v = np.array([1.0, 2.0, 3.0])
mat = np.array([[0.0, 1.0, 0.0],
[1.0, 0.0, 1.0],
[1.0, 1.0, 1.0]])
mat_set_diag = np.array([[1.0, 1.0, 0.0],
[1.0, 2.0, 1.0],
[1.0, 1.0, 3.0]])
output = tf.batch_matrix_set_diag(mat, v)
self.assertEqual((3, 3), output.get_shape())
self.assertAllEqual(mat_set_diag, output.eval())
def testGradWithNoShapeInformation(self):
with self.test_session(use_gpu=self._use_gpu) as sess:
v = tf.placeholder(dtype=tf.float32)
mat = tf.placeholder(dtype=tf.float32)
grad_input = tf.placeholder(dtype=tf.float32)
output = tf.batch_matrix_set_diag(mat, v)
grads = tf.gradients(output, [mat, v], grad_ys=grad_input)
grad_input_val = np.random.rand(3, 3).astype(np.float32)
grad_vals = sess.run(
grads, feed_dict={v: 2 * np.ones(3), mat: np.ones((3, 3)),
grad_input: grad_input_val})
self.assertAllEqual(np.diag(grad_input_val), grad_vals[1])
self.assertAllEqual(grad_input_val - np.diag(np.diag(grad_input_val)),
grad_vals[0])
def testGrad(self):
shapes = ((3, 4, 4), (7, 4, 8, 8))
with self.test_session(use_gpu=self._use_gpu):
for shape in shapes:
x = tf.constant(np.random.rand(*shape), dtype=tf.float32)
x_diag = tf.constant(np.random.rand(*shape[:-1]), dtype=tf.float32)
y = tf.batch_matrix_set_diag(x, x_diag)
error_x = tf.test.compute_gradient_error(x, x.get_shape().as_list(),
y, y.get_shape().as_list())
self.assertLess(error_x, 1e-4)
error_x_diag = tf.test.compute_gradient_error(
x_diag, x_diag.get_shape().as_list(),
y, y.get_shape().as_list())
self.assertLess(error_x_diag, 1e-4)
def testGradWithNoShapeInformation(self):
with self.test_session(use_gpu=self._use_gpu) as sess:
v = tf.placeholder(dtype=tf.float32)
mat = tf.placeholder(dtype=tf.float32)
grad_input = tf.placeholder(dtype=tf.float32)
output = tf.batch_matrix_set_diag(mat, v)
grads = tf.gradients(output, [mat, v], grad_ys=grad_input)
grad_input_val = np.random.rand(3, 3).astype(np.float32)
grad_vals = sess.run(
grads, feed_dict={v: 2 * np.ones(3), mat: np.ones((3, 3)),
grad_input: grad_input_val})
self.assertAllEqual(np.diag(grad_input_val), grad_vals[1])
self.assertAllEqual(grad_input_val - np.diag(np.diag(grad_input_val)),
grad_vals[0])
def testGrad(self):
shapes = ((3, 4, 4), (7, 4, 8, 8))
with self.test_session(use_gpu=self._use_gpu):
for shape in shapes:
x = tf.constant(np.random.rand(*shape), dtype=tf.float32)
x_diag = tf.constant(np.random.rand(*shape[:-1]), dtype=tf.float32)
y = tf.batch_matrix_set_diag(x, x_diag)
error_x = tf.test.compute_gradient_error(x, x.get_shape().as_list(),
y, y.get_shape().as_list())
self.assertLess(error_x, 1e-4)
error_x_diag = tf.test.compute_gradient_error(
x_diag, x_diag.get_shape().as_list(),
y, y.get_shape().as_list())
self.assertLess(error_x_diag, 1e-4)
def testBatchVector(self):
with self.test_session(use_gpu=self._use_gpu):
v_batch = np.array([[-1.0, -2.0, -3.0], [-4.0, -5.0, -6.0]])
mat_batch = np.array([[[1.0, 0.0, 3.0], [0.0, 2.0, 0.0],
[1.0, 0.0, 3.0]],
[[4.0, 0.0, 4.0], [0.0, 5.0, 0.0],
[2.0, 0.0, 6.0]]])
mat_set_diag_batch = np.array([[[-1.0, 0.0, 3.0], [0.0, -2.0, 0.0],
[1.0, 0.0, -3.0]],
[[-4.0, 0.0, 4.0], [0.0, -5.0, 0.0],
[2.0, 0.0, -6.0]]])
output = tf.batch_matrix_set_diag(mat_batch, v_batch)
self.assertEqual((2, 3, 3), output.get_shape())
self.assertAllEqual(mat_set_diag_batch, output.eval())
def testBatchVector(self):
with self.test_session(use_gpu=self._use_gpu):
v_batch = np.array([[-1.0, -2.0, -3.0],
[-4.0, -5.0, -6.0]])
mat_batch = np.array(
[[[1.0, 0.0, 3.0],
[0.0, 2.0, 0.0],
[1.0, 0.0, 3.0]],
[[4.0, 0.0, 4.0],
[0.0, 5.0, 0.0],
[2.0, 0.0, 6.0]]])
mat_set_diag_batch = np.array(
[[[-1.0, 0.0, 3.0],
[0.0, -2.0, 0.0],
[1.0, 0.0, -3.0]],
[[-4.0, 0.0, 4.0],
[0.0, -5.0, 0.0],
[2.0, 0.0, -6.0]]])
output = tf.batch_matrix_set_diag(mat_batch, v_batch)
self.assertEqual((2, 3, 3), output.get_shape())
self.assertAllEqual(mat_set_diag_batch, output.eval())
def testInvalidShape(self):
with self.assertRaisesRegexp(ValueError, "must have rank at least 2"):
tf.batch_matrix_set_diag(0, [0])
with self.assertRaisesRegexp(ValueError, "must have rank at least 1"):
tf.batch_matrix_set_diag([[0]], 0)
def testInvalidShape(self):
with self.assertRaisesRegexp(ValueError, "must have rank at least 2"):
tf.batch_matrix_set_diag(0, [0])
with self.assertRaisesRegexp(ValueError, "must have rank at least 1"):
tf.batch_matrix_set_diag([[0]], 0)
