def test_DTNNEmbedding_pickle(): tg = TensorGraph() atom_numbers = Feature(shape=(None, 23), dtype=tf.int32) Embedding = DTNNEmbedding(in_layers=[atom_numbers]) tg.add_output(Embedding) tg.set_loss(Embedding) tg.build() tg.save()
def build_graph(self):
self.smiles_seqs = Feature(shape=(None, self.seq_length), dtype=tf.int32)
# Character embedding
self.Embedding = DTNNEmbedding(
n_embedding=self.n_embedding,
periodic_table_length=len(self.char_dict.keys()) + 1,
in_layers=[self.smiles_seqs])
self.pooled_outputs = []
self.conv_layers = []
for filter_size, num_filter in zip(self.kernel_sizes, self.num_filters):
# Multiple convolutional layers with different filter widths
self.conv_layers.append(
Conv1D(
kernel_size=filter_size,
filters=num_filter,
padding='valid',
in_layers=[self.Embedding]))
# Max-over-time pooling
self.pooled_outputs.append(
ReduceMax(axis=1, in_layers=[self.conv_layers[-1]]))
# Concat features from all filters(one feature per filter)
concat_outputs = Concat(axis=1, in_layers=self.pooled_outputs)
dropout = Dropout(dropout_prob=self.dropout, in_layers=[concat_outputs])
dense = Dense(
out_channels=200, activation_fn=tf.nn.relu, in_layers=[dropout])
# Highway layer from https://arxiv.org/pdf/1505.00387.pdf
self.gather = Highway(in_layers=[dense])
costs = []
self.labels_fd = []
for task in range(self.n_tasks):
if self.mode == "classification":
classification = Dense(
out_channels=2, activation_fn=None, in_layers=[self.gather])
softmax = SoftMax(in_layers=[classification])
self.add_output(softmax)
label = Label(shape=(None, 2))
self.labels_fd.append(label)
cost = SoftMaxCrossEntropy(in_layers=[label, classification])
costs.append(cost)
if self.mode == "regression":
regression = Dense(
out_channels=1, activation_fn=None, in_layers=[self.gather])
self.add_output(regression)
label = Label(shape=(None, 1))
self.labels_fd.append(label)
cost = L2Loss(in_layers=[label, regression])
costs.append(cost)
if self.mode == "classification":
all_cost = Stack(in_layers=costs, axis=1)
elif self.mode == "regression":
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)
def test_dtnn_embedding(self):
"""Test that DTNNEmbedding can be invoked."""
n_embedding = 10
periodic_table_length = 20
test_tensor_input = np.random.permutation(
np.arange(0, periodic_table_length // 2, dtype=np.int32))
with self.session() as sess:
test_tensor = tf.convert_to_tensor(test_tensor_input, dtype=tf.int32)
dtnn_embedding = DTNNEmbedding(
n_embedding=n_embedding, periodic_table_length=periodic_table_length)
dtnn_embedding.create_tensor(in_layers=[test_tensor])
# Layer is wrapper around embedding lookup, tested that then
sess.run(tf.global_variables_initializer())
out_tensor = dtnn_embedding.out_tensor.eval()
embedding_val = dtnn_embedding.trainable_variables[0].eval()
expected_output = embedding_val[test_tensor_input]
self.assertAllClose(out_tensor, expected_output)
self.assertAllClose(out_tensor.shape,
(periodic_table_length // 2, n_embedding))
def test_dtnn_embedding(self):
"""Test that DTNNEmbedding can be invoked."""
n_embedding = 10
periodic_table_length = 20
test_tensor_input = np.random.permutation(
np.arange(0, periodic_table_length // 2, dtype=np.int32))
with self.session() as sess:
test_tensor = tf.convert_to_tensor(test_tensor_input, dtype=tf.int32)
dtnn_embedding = DTNNEmbedding(
n_embedding=n_embedding, periodic_table_length=periodic_table_length)
dtnn_embedding.create_tensor(in_layers=[test_tensor])
# Layer is wrapper around embedding lookup, tested that then
sess.run(tf.global_variables_initializer())
out_tensor = dtnn_embedding.out_tensor.eval()
embedding_val = dtnn_embedding.embedding_list.eval()
expected_output = embedding_val[test_tensor_input]
self.assertAllClose(out_tensor, expected_output)
self.assertAllClose(out_tensor.shape,
(periodic_table_length // 2, n_embedding))
def _build_graph(self):
self.smiles_seqs = Feature(shape=(None, self.seq_length),
dtype=tf.int32)
# Character embedding
Embedding = DTNNEmbedding(
n_embedding=self.n_embedding,
periodic_table_length=len(self.char_dict.keys()) + 1,
in_layers=[self.smiles_seqs])
pooled_outputs = []
conv_layers = []
for filter_size, num_filter in zip(self.kernel_sizes,
self.num_filters):
# Multiple convolutional layers with different filter widths
conv_layers.append(
Conv1D(kernel_size=filter_size,
filters=num_filter,
padding='valid',
in_layers=[Embedding]))
# Max-over-time pooling
pooled_outputs.append(
ReduceMax(axis=1, in_layers=[conv_layers[-1]]))
# Concat features from all filters(one feature per filter)
concat_outputs = Concat(axis=1, in_layers=pooled_outputs)
dropout = Dropout(dropout_prob=self.dropout,
in_layers=[concat_outputs])
dense = Dense(out_channels=200,
activation_fn=tf.nn.relu,
in_layers=[dropout])
# Highway layer from https://arxiv.org/pdf/1505.00387.pdf
gather = Highway(in_layers=[dense])
if self.mode == "classification":
logits = Dense(out_channels=self.n_tasks * 2,
activation_fn=None,
in_layers=[gather])
logits = Reshape(shape=(-1, self.n_tasks, 2), in_layers=[logits])
output = SoftMax(in_layers=[logits])
self.add_output(output)
labels = Label(shape=(None, self.n_tasks, 2))
loss = SoftMaxCrossEntropy(in_layers=[labels, logits])
else:
vals = Dense(out_channels=self.n_tasks * 1,
activation_fn=None,
in_layers=[gather])
vals = Reshape(shape=(-1, self.n_tasks, 1), in_layers=[vals])
self.add_output(vals)
labels = Label(shape=(None, self.n_tasks, 1))
loss = ReduceSum(L2Loss(in_layers=[labels, vals]))
weights = Weights(shape=(None, self.n_tasks))
weighted_loss = WeightedError(in_layers=[loss, 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])
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)