def build(self):
# Create target inputs
self.label_placeholder = Input(tensor=K.placeholder(
shape=(None,self.n_tasks), name="label_placeholder", dtype='bool'))
self.weight_placeholder = Input(tensor=K.placeholder(
shape=(None,self.n_tasks), name="weight_placholder", dtype='float32'))
# Create final dense layer from keras
feat = self.model.return_outputs()
output = model_ops.multitask_logits(
feat, self.n_tasks)
return output
def build(self):
# Create target inputs
self.label_placeholder = Input(tensor=K.placeholder(
shape=(None,self.n_tasks), name="label_placeholder", dtype='bool'))
self.weight_placeholder = Input(tensor=K.placeholder(
shape=(None,self.n_tasks), name="weight_placholder", dtype='float32'))
# Create final dense layer from keras
feat = self.model.return_outputs()
output = model_ops.multitask_logits(
feat, self.n_tasks)
return output
def build(self, graph, name_scopes, training):
"""Constructs the graph architecture as specified in its config.
This method creates the following Placeholders:
mol_features: Molecule descriptor (e.g. fingerprint) tensor with shape
batch_size x n_features.
"""
placeholder_scope = TensorflowGraph.get_placeholder_scope(
graph, name_scopes)
n_features = self.n_features
with graph.as_default():
with placeholder_scope:
self.mol_features = tf.placeholder(
tf.float32,
shape=[None, n_features],
name='mol_features')
layer_sizes = self.layer_sizes
weight_init_stddevs = self.weight_init_stddevs
bias_init_consts = self.bias_init_consts
dropouts = self.dropouts
lengths_set = {
len(layer_sizes),
len(weight_init_stddevs),
len(bias_init_consts),
len(dropouts),
}
assert len(lengths_set) == 1, 'All layer params must have same length.'
n_layers = lengths_set.pop()
assert n_layers > 0, 'Must have some layers defined.'
prev_layer = self.mol_features
prev_layer_size = n_features
for i in range(n_layers):
layer = tf.nn.relu(model_ops.fully_connected_layer(
tensor=prev_layer,
size=layer_sizes[i],
weight_init=tf.truncated_normal(
shape=[prev_layer_size, layer_sizes[i]],
stddev=weight_init_stddevs[i]),
bias_init=tf.constant(value=bias_init_consts[i],
shape=[layer_sizes[i]])))
layer = model_ops.dropout(layer, dropouts[i], training)
prev_layer = layer
prev_layer_size = layer_sizes[i]
output = model_ops.multitask_logits(
layer, self.n_tasks)
return output
def build(self, graph, name_scopes, training):
"""Constructs the graph architecture as specified in its config.
This method creates the following Placeholders:
mol_features: Molecule descriptor (e.g. fingerprint) tensor with shape
batch_size x n_features.
"""
placeholder_scope = TensorflowGraph.get_placeholder_scope(
graph, name_scopes)
n_features = self.n_features
with graph.as_default():
with placeholder_scope:
self.mol_features = tf.placeholder(tf.float32,
shape=[None, n_features],
name='mol_features')
layer_sizes = self.layer_sizes
weight_init_stddevs = self.weight_init_stddevs
bias_init_consts = self.bias_init_consts
dropouts = self.dropouts
lengths_set = {
len(layer_sizes),
len(weight_init_stddevs),
len(bias_init_consts),
len(dropouts),
}
assert len(
lengths_set) == 1, 'All layer params must have same length.'
n_layers = lengths_set.pop()
assert n_layers > 0, 'Must have some layers defined.'
prev_layer = self.mol_features
prev_layer_size = n_features
for i in range(n_layers):
layer = tf.nn.relu(
model_ops.fully_connected_layer(
tensor=prev_layer,
size=layer_sizes[i],
weight_init=tf.truncated_normal(
shape=[prev_layer_size, layer_sizes[i]],
stddev=weight_init_stddevs[i]),
bias_init=tf.constant(value=bias_init_consts[i],
shape=[layer_sizes[i]])))
layer = model_ops.dropout(layer, dropouts[i], training)
prev_layer = layer
prev_layer_size = layer_sizes[i]
output = model_ops.multitask_logits(layer, self.n_tasks)
return output
def test_multitask_logits(self):
with self.test_session() as sess:
num_tasks = 3
np.random.seed(FLAGS.test_random_seed)
features = np.random.random((5, 100))
logits_t = model_ops.multitask_logits(
tf.constant(features, dtype=tf.float32), num_tasks)
sess.run(tf.initialize_all_variables())
output = sess.run(tf.trainable_variables() + logits_t)
w = output[0:-3:2]
b = output[1:-3:2]
logits = output[-3:]
for i in range(num_tasks):
expected = np.dot(features, w[i]) + b[i]
self.assertAllClose(logits[i], expected, rtol=1e-5, atol=1e-5)
