def test_dtnn_gather(self):
"""Test that DTNNGather can be invoked."""
n_embedding = 2
n_outputs = 2
layer_sizes = [2]
output_activation = False
init_method = 'one'
activation = 'sigmoid'
inputs_np = np.array([[1, -1], [1, -1], [1, -1]])
atom_membership_np = np.array([0, 0, 1])
expected_output = np.array([[2, 2], [1, 1]])
with self.session() as sess:
inputs_tf = tf.convert_to_tensor(inputs_np, dtype=tf.float32)
atom_membership_tf = tf.convert_to_tensor(atom_membership_np,
dtype=tf.int32)
dtnn_gather = DTNNGather(n_embedding=n_embedding,
n_outputs=n_outputs,
layer_sizes=layer_sizes,
output_activation=output_activation,
init=init_method,
activation=activation)
dtnn_gather.create_tensor(
in_layers=[inputs_tf, atom_membership_tf])
sess.run(tf.global_variables_initializer())
output = dtnn_gather.out_tensor.eval()
self.assertAllClose(expected_output, output)
self.assertEqual(expected_output.shape, output.shape)
def test_dtnn_gather(self):
"""Test that DTNNGather can be invoked."""
n_embedding = 2
n_outputs = 2
layer_sizes = [2]
output_activation = False
init_method = 'one'
activation = 'sigmoid'
inputs_np = np.array([[1, -1], [1, -1], [1, -1]])
atom_membership_np = np.array([0, 0, 1])
expected_output = np.array([[2, 2], [1, 1]])
with self.session() as sess:
inputs_tf = tf.convert_to_tensor(inputs_np, dtype=tf.float32)
atom_membership_tf = tf.convert_to_tensor(
atom_membership_np, dtype=tf.int32)
dtnn_gather = DTNNGather(
n_embedding=n_embedding,
n_outputs=n_outputs,
layer_sizes=layer_sizes,
output_activation=output_activation,
init=init_method,
activation=activation)
dtnn_gather.create_tensor(in_layers=[inputs_tf, atom_membership_tf])
sess.run(tf.global_variables_initializer())
output = dtnn_gather.out_tensor.eval()
self.assertAllClose(expected_output, output)
self.assertEqual(expected_output.shape, output.shape)
def test_DTNNGather_pickle(): tg = TensorGraph() atom_features = Feature(shape=(None, 30)) atom_membership = Feature(shape=(None,), dtype=tf.int32) Gather = DTNNGather(in_layers=[atom_features, atom_membership]) tg.add_output(Gather) tg.set_loss(Gather) tg.build() tg.save()
def build_graph(self):
"""Building graph structures:
Features => DTNNEmbedding => DTNNStep => DTNNStep => DTNNGather => Regression
"""
self.atom_number = Feature(shape=(None, ), dtype=tf.int32)
self.distance = Feature(shape=(None, self.n_distance))
self.atom_membership = Feature(shape=(None, ), dtype=tf.int32)
self.distance_membership_i = Feature(shape=(None, ), dtype=tf.int32)
self.distance_membership_j = Feature(shape=(None, ), dtype=tf.int32)
dtnn_embedding = DTNNEmbedding(n_embedding=self.n_embedding,
in_layers=[self.atom_number])
if self.dropout > 0.0:
dtnn_embedding = Dropout(self.dropout, in_layers=dtnn_embedding)
dtnn_layer1 = DTNNStep(n_embedding=self.n_embedding,
n_distance=self.n_distance,
in_layers=[
dtnn_embedding, self.distance,
self.distance_membership_i,
self.distance_membership_j
])
if self.dropout > 0.0:
dtnn_layer1 = Dropout(self.dropout, in_layers=dtnn_layer1)
dtnn_layer2 = DTNNStep(n_embedding=self.n_embedding,
n_distance=self.n_distance,
in_layers=[
dtnn_layer1, self.distance,
self.distance_membership_i,
self.distance_membership_j
])
if self.dropout > 0.0:
dtnn_layer2 = Dropout(self.dropout, in_layers=dtnn_layer2)
dtnn_gather = DTNNGather(n_embedding=self.n_embedding,
layer_sizes=[self.n_hidden],
n_outputs=self.n_tasks,
output_activation=self.output_activation,
in_layers=[dtnn_layer2, self.atom_membership])
if self.dropout > 0.0:
dtnn_gather = Dropout(self.dropout, in_layers=dtnn_gather)
n_tasks = self.n_tasks
weights = Weights(shape=(None, n_tasks))
labels = Label(shape=(None, n_tasks))
output = Reshape(
shape=(None, n_tasks),
in_layers=[Dense(in_layers=dtnn_gather, out_channels=n_tasks)])
self.add_output(output)
weighted_loss = ReduceSum(L2Loss(in_layers=[labels, output, weights]))
self.set_loss(weighted_loss)
def build_graph(self):
"""Building graph structures:
Features => DTNNEmbedding => DTNNStep => DTNNStep => DTNNGather => Regression
"""
self.atom_number = Feature(shape=(None,), dtype=tf.int32)
self.distance = Feature(shape=(None, self.n_distance))
self.atom_membership = Feature(shape=(None,), dtype=tf.int32)
self.distance_membership_i = Feature(shape=(None,), dtype=tf.int32)
self.distance_membership_j = Feature(shape=(None,), dtype=tf.int32)
dtnn_embedding = DTNNEmbedding(
n_embedding=self.n_embedding, in_layers=[self.atom_number])
dtnn_layer1 = DTNNStep(
n_embedding=self.n_embedding,
n_distance=self.n_distance,
in_layers=[
dtnn_embedding, self.distance, self.distance_membership_i,
self.distance_membership_j
])
dtnn_layer2 = DTNNStep(
n_embedding=self.n_embedding,
n_distance=self.n_distance,
in_layers=[
dtnn_layer1, self.distance, self.distance_membership_i,
self.distance_membership_j
])
dtnn_gather = DTNNGather(
n_embedding=self.n_embedding,
layer_sizes=[self.n_hidden],
n_outputs=self.n_tasks,
output_activation=self.output_activation,
in_layers=[dtnn_layer2, self.atom_membership])
costs = []
self.labels_fd = []
for task in range(self.n_tasks):
regression = DTNNExtract(task, in_layers=[dtnn_gather])
self.add_output(regression)
label = Label(shape=(None, 1))
self.labels_fd.append(label)
cost = L2Loss(in_layers=[label, regression])
costs.append(cost)
all_cost = Stack(in_layers=costs, axis=1)
self.weights = Weights(shape=(None, self.n_tasks))
loss = WeightedError(in_layers=[all_cost, self.weights])
self.set_loss(loss)
