def test_reshape_inputs(self):
"""Test that layers can automatically reshape inconsistent inputs."""
value1 = np.random.uniform(size=(2, 3)).astype(np.float32)
value2 = np.random.uniform(size=(1, 6, 1)).astype(np.float32)
with self.session() as sess:
out_tensor = ReduceSquareDifference()(tf.constant(value1),
tf.constant(value2))
result = out_tensor.eval()
diff = value1.reshape((1, 6, 1)) - value2
loss = np.mean(diff**2)
assert (loss - result) / loss < 1e-6
def test_reshape_inputs(self):
"""Test that layers can automatically reshape inconsistent inputs."""
value1 = np.random.uniform(size=(2, 3)).astype(np.float32)
value2 = np.random.uniform(size=(1, 6, 1)).astype(np.float32)
with self.session() as sess:
out_tensor = ReduceSquareDifference()(tf.constant(value1),
tf.constant(value2))
result = out_tensor.eval()
diff = value1.reshape((1, 6, 1)) - value2
loss = np.mean(diff**2)
assert (loss - result) / loss < 1e-6
def test_reduce_square_difference(self):
"""Test that ReduceSquareDifference can be invoked."""
batch_size = 10
n_features = 5
in_tensor_1 = np.random.rand(batch_size, n_features)
in_tensor_2 = np.random.rand(batch_size, n_features)
with self.session() as sess:
in_tensor_1 = tf.convert_to_tensor(in_tensor_1, dtype=tf.float32)
in_tensor_2 = tf.convert_to_tensor(in_tensor_2, dtype=tf.float32)
out_tensor = ReduceSquareDifference()(in_tensor_1, in_tensor_2)
out_tensor = out_tensor.eval()
assert isinstance(out_tensor, np.float32)
def test_reduce_square_difference(self):
"""Test that ReduceSquareDifference can be invoked."""
batch_size = 10
n_features = 5
in_tensor_1 = np.random.rand(batch_size, n_features)
in_tensor_2 = np.random.rand(batch_size, n_features)
with self.session() as sess:
in_tensor_1 = tf.convert_to_tensor(in_tensor_1, dtype=tf.float32)
in_tensor_2 = tf.convert_to_tensor(in_tensor_2, dtype=tf.float32)
out_tensor = ReduceSquareDifference()(in_tensor_1, in_tensor_2)
out_tensor = out_tensor.eval()
assert isinstance(out_tensor, np.float32)