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 build_graph(self):
# inputs placeholder
self.inputs = Feature(shape=(None, self.image_size, self.image_size,
3),
dtype=tf.float32)
# data preprocessing and augmentation
in_layer = DRAugment(self.augment,
self.batch_size,
size=(self.image_size, self.image_size),
in_layers=[self.inputs])
# first conv layer
in_layer = Conv2D(int(self.n_init_kernel),
kernel_size=7,
activation_fn=None,
in_layers=[in_layer])
in_layer = BatchNorm(in_layers=[in_layer])
in_layer = ReLU(in_layers=[in_layer])
# downsample by max pooling
res_in = MaxPool2D(ksize=[1, 3, 3, 1],
strides=[1, 2, 2, 1],
in_layers=[in_layer])
for ct_module in range(self.n_downsample - 1):
# each module is a residual convolutional block
# followed by a convolutional downsample layer
in_layer = Conv2D(int(self.n_init_kernel * 2**(ct_module - 1)),
kernel_size=1,
activation_fn=None,
in_layers=[res_in])
in_layer = BatchNorm(in_layers=[in_layer])
in_layer = ReLU(in_layers=[in_layer])
in_layer = Conv2D(int(self.n_init_kernel * 2**(ct_module - 1)),
kernel_size=3,
activation_fn=None,
in_layers=[in_layer])
in_layer = BatchNorm(in_layers=[in_layer])
in_layer = ReLU(in_layers=[in_layer])
in_layer = Conv2D(int(self.n_init_kernel * 2**ct_module),
kernel_size=1,
activation_fn=None,
in_layers=[in_layer])
res_a = BatchNorm(in_layers=[in_layer])
res_out = res_in + res_a
res_in = Conv2D(int(self.n_init_kernel * 2**(ct_module + 1)),
kernel_size=3,
stride=2,
in_layers=[res_out])
res_in = BatchNorm(in_layers=[res_in])
# max pooling over the final outcome
in_layer = ReduceMax(axis=(1, 2), in_layers=[res_in])
for layer_size in self.n_fully_connected:
# fully connected layers
in_layer = Dense(layer_size,
activation_fn=tf.nn.relu,
in_layers=[in_layer])
# dropout for dense layers
#in_layer = Dropout(0.25, in_layers=[in_layer])
logit_pred = Dense(self.n_tasks * self.n_classes,
activation_fn=None,
in_layers=[in_layer])
logit_pred = Reshape(shape=(None, self.n_tasks, self.n_classes),
in_layers=[logit_pred])
weights = Weights(shape=(None, self.n_tasks))
labels = Label(shape=(None, self.n_tasks), dtype=tf.int32)
output = SoftMax(logit_pred)
self.add_output(output)
loss = SparseSoftMaxCrossEntropy(in_layers=[labels, logit_pred])
weighted_loss = WeightedError(in_layers=[loss, weights])
# weight decay regularizer
# weighted_loss = WeightDecay(0.1, 'l2', in_layers=[weighted_loss])
self.set_loss(weighted_loss)