def testMultiplyInverseNotTupleWithBias(self):
with tf.Graph().as_default(), self.test_session() as sess:
tf.set_random_seed(200)
params = [tf.random_normal((2, 2, 2, 2))]
inputs = tf.random_normal((2, 2, 2, 2))
outputs = tf.random_normal((2, 2, 2, 2))
block = fb.ConvKFCBasicFB(
lc.LayerCollection(), params=params, padding='SAME')
block.register_additional_tower(inputs, outputs)
self.assertTrue(block._has_bias)
grads = outputs**2
block.instantiate_factors(((grads,),), 0.5)
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()
# Make sure our inverse is something other than the identity.
sess.run(tf.global_variables_initializer())
sess.run(block._input_factor.make_inverse_update_ops())
sess.run(block._output_factor.make_inverse_update_ops())
vector = np.arange(1, 19).reshape(9, 2).astype(np.float32)
output = block.multiply_inverse(tf.constant(vector))
self.assertAllClose([0.136455, 0.27291], sess.run(output)[0])
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 _testConvKFCBasicFBInitParams(self, params):
with tf.Graph().as_default():
tf.set_random_seed(200)
if isinstance(params, (list, tuple)):
params = [tf.constant(param) for param in params]
else:
params = tf.constant(params)
inputs = tf.random_normal((2, 2, 2))
outputs = tf.random_normal((2, 2, 2))
block = fb.ConvKFCBasicFB(
lc.LayerCollection(), params=params, padding='SAME')
block.register_additional_tower(inputs, outputs)
self.assertAllEqual([outputs], block.tensors_to_compute_grads())
