def testMultipleOfNoneGradRaisesError(self):
gradient = constant_op.constant(self._grad_vec, dtype=dtypes.float32)
variable = variables_lib.Variable(array_ops.zeros_like(gradient))
grad_to_var = (None, variable)
gradient_multipliers = {variable: self._multiplier}
with self.assertRaises(ValueError):
learning.multiply_gradients(grad_to_var, gradient_multipliers)
def transform_grads_fn(grads):
if gradient_multipliers:
with tf.name_scope('multiply_grads'):
grads = multiply_gradients(grads, gradient_multipliers)
# Clip gradients.
if clip_gradient_norm > 0:
with tf.name_scope('clip_grads'):
grads = clip_gradient_norms(grads, clip_gradient_norm)
return grads
def testMultipleGradientsWithVariables(self):
gradient = constant_op.constant(self._grad_vec, dtype=dtypes.float32)
variable = variables_lib.Variable(array_ops.zeros_like(gradient))
grad_to_var = (gradient, variable)
gradient_multipliers = {variable: self._multiplier}
[grad_to_var] = learning.multiply_gradients([grad_to_var],
gradient_multipliers)
# Ensure the variable passed through.
self.assertEqual(grad_to_var[1], variable)
with self.test_session() as sess:
actual_gradient = sess.run(grad_to_var[0])
np_testing.assert_almost_equal(actual_gradient, self._multiplied_grad_vec,
5)
def testTensorMultiplierOfGradient(self):
gradient = constant_op.constant(self._grad_vec, dtype=dtypes.float32)
variable = variables_lib.Variable(array_ops.zeros_like(gradient))
multiplier_flag = variables_lib.Variable(True)
tensor_multiplier = array_ops.where(multiplier_flag, self._multiplier, 1.0)
grad_to_var = (gradient, variable)
gradient_multipliers = {variable: tensor_multiplier}
[grad_to_var] = learning.multiply_gradients([grad_to_var],
gradient_multipliers)
with self.test_session() as sess:
sess.run(variables_lib.global_variables_initializer())
gradient_true_flag = sess.run(grad_to_var[0])
sess.run(multiplier_flag.assign(False))
gradient_false_flag = sess.run(grad_to_var[0])
np_testing.assert_almost_equal(gradient_true_flag,
self._multiplied_grad_vec, 5)
np_testing.assert_almost_equal(gradient_false_flag, self._grad_vec, 5)
def testIndexedSlicesGradIsMultiplied(self):
values = constant_op.constant(self._grad_vec, dtype=dtypes.float32)
indices = constant_op.constant([0, 1, 2], dtype=dtypes.int32)
dense_shape = constant_op.constant(
[self._grad_vec.size], dtype=dtypes.int32)
gradient = ops.IndexedSlices(values, indices, dense_shape)
variable = variables_lib.Variable(array_ops.zeros((1, 3)))
grad_to_var = (gradient, variable)
gradient_multipliers = {variable: self._multiplier}
[grad_to_var] = learning.multiply_gradients([grad_to_var],
gradient_multipliers)
# Ensure the built IndexedSlice has the right form.
self.assertEqual(grad_to_var[1], variable)
self.assertEqual(grad_to_var[0].indices, indices)
self.assertEqual(grad_to_var[0].dense_shape, dense_shape)
with self.test_session() as sess:
actual_gradient = sess.run(grad_to_var[0].values)
np_testing.assert_almost_equal(actual_gradient, self._multiplied_grad_vec,
5)
def testNonDictMultiplierRaisesError(self):
gradient = constant_op.constant(self._grad_vec, dtype=dtypes.float32)
variable = variables_lib.Variable(array_ops.zeros_like(gradient))
grad_to_var = (gradient, variable)
with self.assertRaises(ValueError):
learning.multiply_gradients([grad_to_var], 3)
