def setUp(self):
RnnClass = self.get_mdrnn_class()
self.rnn2d = RnnClass(units=1,
input_shape=(None, None, 1),
kernel_initializer=initializers.Identity(),
recurrent_initializer=initializers.Identity(1),
bias_initializer=initializers.Constant(-1),
return_sequences=True,
activation=None)
self.x = np.arange(6).reshape((1, 2, 3, 1))
self.initial_state = [tf.ones(shape=(1, 1)), tf.ones(shape=(1, 1))]
def test_result(self):
rnn2d = MDRNN(units=1, input_shape=(None, None, 1),
kernel_initializer=initializers.Identity(),
recurrent_initializer=initializers.Identity(1),
bias_initializer=initializers.Constant(-1),
return_sequences=True,
activation=None)
x = np.arange(6).reshape((1, 2, 3, 1))
actual = rnn2d.call(x)
desired = np.array([
[-1, -1, 0],
[1, 3, 7]
]).reshape((1, 2, 3, 1))
np.testing.assert_almost_equal(desired, actual.numpy(), 6)
def test_2drnn_output_when_providing_initial_state(self):
rnn2d = MDRNN(units=1, input_shape=(None, None, 1),
kernel_initializer=initializers.Identity(),
recurrent_initializer=initializers.Identity(1),
bias_initializer=initializers.Constant(-1),
return_sequences=True,
activation=None)
x = np.arange(6).reshape((1, 2, 3, 1))
initial_state = [tf.ones(shape=(1, 1)), tf.ones(shape=(1, 1))]
actual = rnn2d.call(x, initial_state=initial_state)
desired = np.array([
[1, 1, 2],
[3, 7, 13]
]).reshape((1, 2, 3, 1))
np.testing.assert_almost_equal(desired, actual.numpy(), 6)
def test_result_after_running_rnn_on_3d_input(self):
rnn3d = MDRNN(units=1,
input_shape=(None, None, None, 1),
kernel_initializer=initializers.Identity(),
recurrent_initializer=initializers.Identity(1),
bias_initializer=initializers.Constant(1),
return_sequences=True,
return_state=True,
activation=None)
x = np.arange(2 * 2 * 2).reshape((1, 2, 2, 2, 1))
outputs, state = rnn3d.call(x)
desired = np.array([[[1, 3], [4, 11]], [[6, 15], [17, 51]]]).reshape(
(1, 2, 2, 2, 1))
np.testing.assert_almost_equal(desired, outputs.numpy(), 6)
desired_state = desired[:, -1, -1, -1]
np.testing.assert_almost_equal(desired_state, state.numpy(), 6)
def test_recurrent_weights_are_working(self):
mdrnn = self.create_default_mdrnn(
kernel_initializer=initializers.Zeros(),
recurrent_initializer=initializers.Identity(),
bias_initializer=initializers.Zeros(),
activation=None
)
initial_state = np.array([1, 2, 3]).reshape(1, -1)
initial_state = tf.constant(initial_state, dtype=tf.float32)
expected_result = np.array([[1, 2, 3]])
self.assert_model_predicts_correct_result(expected_result, mdrnn, self.x,
initial_state=initial_state)
def test_kernel_weights_are_working(self):
mdrnn = self.create_default_mdrnn(
kernel_initializer=initializers.Identity(),
recurrent_initializer=initializers.Zeros(),
bias_initializer=initializers.Zeros(),
activation=None,
return_sequences=True
)
x1 = np.array([1, 2, 3])
x = np.array([[x1]])
a = mdrnn.call(x)
expected_result = x.copy()
np.testing.assert_almost_equal(expected_result, a.numpy(), 8)