def _build_graph(self):
self.one_hot_seq = Feature(shape=(None, self.pad_length,
self.num_amino_acids),
dtype=tf.float32)
conv1 = Conv1D(kernel_size=2,
filters=512,
in_layers=[self.one_hot_seq])
maxpool1 = MaxPool1D(strides=2, padding="VALID", in_layers=[conv1])
conv2 = Conv1D(kernel_size=3, filters=512, in_layers=[maxpool1])
flattened = Flatten(in_layers=[conv2])
dense1 = Dense(out_channels=400,
in_layers=[flattened],
activation_fn=tf.nn.tanh)
dropout = Dropout(dropout_prob=self.dropout_p, in_layers=[dense1])
output = Dense(out_channels=1, in_layers=[dropout], activation_fn=None)
self.add_output(output)
if self.mode == "regression":
label = Label(shape=(None, 1))
loss = L2Loss(in_layers=[label, output])
else:
raise NotImplementedError(
"Classification support not added yet. Missing details in paper."
)
weights = Weights(shape=(None, ))
weighted_loss = WeightedError(in_layers=[loss, weights])
self.set_loss(weighted_loss)
def test_Conv1D_pickle(): tg = TensorGraph() feature = Feature(shape=(tg.batch_size, 1, 1)) conv = Conv1D(2, 1, in_layers=feature) tg.add_output(conv) tg.set_loss(conv) 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 _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 test_conv_1D(self):
"""Test that Conv1D can be invoked."""
width = 5
in_channels = 2
out_channels = 3
batch_size = 10
in_tensor = np.random.rand(batch_size, width, in_channels)
with self.test_session() as sess:
in_tensor = tf.convert_to_tensor(in_tensor, dtype=tf.float32)
out_tensor = Conv1D(width, out_channels)(in_tensor)
sess.run(tf.global_variables_initializer())
out_tensor = out_tensor.eval()
assert out_tensor.shape == (batch_size, width, out_channels)
def test_conv_1D(self):
"""Test that Conv1D can be invoked."""
width = 5
in_channels = 2
filters = 3
kernel_size = 2
batch_size = 10
in_tensor = np.random.rand(batch_size, width, in_channels)
with self.session() as sess:
in_tensor = tf.convert_to_tensor(in_tensor, dtype=tf.float32)
out_tensor = Conv1D(filters, kernel_size)(in_tensor)
sess.run(tf.global_variables_initializer())
out_tensor = out_tensor.eval()
self.assertEqual(out_tensor.shape[0], batch_size)
self.assertEqual(out_tensor.shape[2], filters)
