def testMultiplyInverseAgainstExplicit(self):
with tf.Graph().as_default(), self.test_session() as sess:
tf.set_random_seed(200)
params = tf.zeros((2, 2, 2, 2))
inputs = tf.zeros((2, 2, 2, 2))
outputs = tf.zeros((2, 2, 2, 2))
block = fb.ConvKFCBasicFB(
lc.LayerCollection(), params=params, padding='SAME')
block.register_additional_tower(inputs, outputs)
grads = outputs**2
damping = 0. # This test is only valid without damping.
block.instantiate_factors(((grads,),), damping)
block._input_factor.instantiate_cov_variables()
block._output_factor.instantiate_cov_variables()
block.register_inverse()
block._input_factor.instantiate_inv_variables()
block._output_factor.instantiate_inv_variables()
sess.run(tf.assign(block._input_factor._cov, _make_psd(8)))
sess.run(tf.assign(block._output_factor._cov, _make_psd(2)))
sess.run(block._input_factor.make_inverse_update_ops())
sess.run(block._output_factor.make_inverse_update_ops())
v_flat = np.arange(16, dtype=np.float32)
vector = utils.column_to_tensors(params, tf.constant(v_flat))
output = block.multiply_inverse(vector)
output_flat = sess.run(utils.tensors_to_column(output)).ravel()
full = sess.run(block.full_fisher_block())
explicit = np.dot(np.linalg.inv(full + damping * np.eye(16)), v_flat)
self.assertAllClose(output_flat, explicit)
def testMultiplyInverseAgainstExplicit(self):
with tf.Graph().as_default(), self.test_session() as sess:
tf.set_random_seed(200)
params = (tf.constant([1., 2.]), tf.constant(3.))
block = fb.FullFB(lc.LayerCollection(), params)
block.register_additional_tower(32)
grads = (tf.constant([2., 3.]), tf.constant(4.))
damping = 0.5
block.instantiate_factors((grads,), damping)
block._factor.instantiate_cov_variables()
block.register_inverse()
block._factor.instantiate_inv_variables()
# Make sure our inverse is something other than the identity.
sess.run(tf.assign(block._factor._cov, _make_psd(3)))
sess.run(block._factor.make_inverse_update_ops())
v_flat = np.array([4., 5., 6.], dtype=np.float32)
vector = utils.column_to_tensors(params, tf.constant(v_flat))
output = block.multiply_inverse(vector)
output_flat = sess.run(utils.tensors_to_column(output)).ravel()
full = sess.run(block.full_fisher_block())
explicit = np.dot(np.linalg.inv(full + damping * np.eye(3)), v_flat)
self.assertAllClose(output_flat, explicit)
def testMultiplyInverseAgainstExplicit(self):
with tf.Graph().as_default(), self.test_session() as sess:
tf.set_random_seed(200)
input_dim, output_dim = 3, 2
inputs = tf.zeros([32, input_dim])
outputs = tf.zeros([32, output_dim])
params = tf.zeros([input_dim, output_dim])
block = fb.FullyConnectedKFACBasicFB(lc.LayerCollection(), has_bias=False)
block.register_additional_tower(inputs, outputs)
grads = outputs**2
damping = 0. # This test is only valid without damping.
block.instantiate_factors(((grads,),), damping)
block._input_factor.instantiate_cov_variables()
block._output_factor.instantiate_cov_variables()
sess.run(tf.global_variables_initializer())
sess.run(block._input_factor._cov.add_to_average(_make_psd(3)))
sess.run(block._output_factor._cov.add_to_average(_make_psd(2)))
block.register_inverse()
block._input_factor.instantiate_inv_variables()
block._output_factor.instantiate_inv_variables()
sess.run(block._input_factor.make_inverse_update_ops())
sess.run(block._output_factor.make_inverse_update_ops())
v_flat = np.arange(6, dtype=np.float32)
vector = utils.column_to_tensors(params, tf.constant(v_flat))
output = block.multiply_inverse(vector)
output_flat = sess.run(utils.tensors_to_column(output)).ravel()
full = sess.run(block.full_fisher_block())
explicit = np.dot(np.linalg.inv(full + damping * np.eye(6)), v_flat)
self.assertAllClose(output_flat, explicit)
def testMultiplyInverseAgainstExplicit(self):
with tf.Graph().as_default(), self.test_session() as sess:
tf.set_random_seed(200)
params = (tf.constant([1., 2.]), tf.constant(3.))
block = fb.NaiveDiagonalFB(lc.LayerCollection(), params)
block.register_additional_tower(32)
grads = (params[0]**2, tf.sqrt(params[1]))
damping = 0.5
block.instantiate_factors((grads,), damping)
block._factor.instantiate_cov_variables()
cov = tf.reshape(tf.constant([2., 3., 4.]), [-1, 1])
sess.run(tf.global_variables_initializer())
sess.run(block._factor._cov.add_to_average(cov))
sess.run(block._factor.make_inverse_update_ops())
v_flat = np.array([4., 5., 6.], dtype=np.float32)
vector = utils.column_to_tensors(params, tf.constant(v_flat))
output = block.multiply_inverse(vector)
output_flat = sess.run(utils.tensors_to_column(output)).ravel()
full = sess.run(block.full_fisher_block())
explicit = np.dot(np.linalg.inv(full + damping * np.eye(3)), v_flat)
self.assertAllClose(output_flat, explicit)
def testTensorsToColumn(self):
with tf.Graph().as_default(), self.test_session() as sess:
tf.set_random_seed(200)
vector = tf.constant(np.array([[0., 1.], [2., 3.]]))
output = utils.tensors_to_column(vector)
self.assertListEqual([4, 1], output.get_shape().as_list())
self.assertAllClose(sess.run(output), np.array([0., 1., 2., 3.])[:, None])
vector = self._fully_connected_layer_params()
output = utils.tensors_to_column(vector)
self.assertListEqual([6, 1], output.get_shape().as_list())
self.assertAllClose(
sess.run(output), np.array([1., 2., 4., 3., 1., 2.])[:, None])
vector = list(vector)
vector.append(tf.constant([[6.], [7.], [8.], [9.]]))
output = utils.tensors_to_column(vector)
self.assertListEqual([10, 1], output.get_shape().as_list())
self.assertAllClose(
sess.run(output),
np.array([1., 2., 4., 3., 1., 2., 6., 7., 8., 9.])[:, None])