def build_graph(self):
self.atom_numbers = Feature(shape=(None, self.max_atoms), dtype=tf.int32)
self.atom_flags = Feature(shape=(None, self.max_atoms, self.max_atoms))
self.atom_feats = Feature(shape=(None, self.max_atoms, self.n_feat))
previous_layer = self.atom_feats
Hiddens = []
for n_hidden in self.layer_structures:
Hidden = AtomicDifferentiatedDense(
self.max_atoms,
n_hidden,
self.atom_number_cases,
activation='tanh',
in_layers=[previous_layer, self.atom_numbers])
Hiddens.append(Hidden)
previous_layer = Hiddens[-1]
costs = []
self.labels_fd = []
for task in range(self.n_tasks):
regression = Dense(
out_channels=1, activation_fn=None, in_layers=[Hiddens[-1]])
output = BPGather(self.max_atoms, in_layers=[regression, self.atom_flags])
self.add_output(output)
label = Label(shape=(None, 1))
self.labels_fd.append(label)
cost = L2Loss(in_layers=[label, output])
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)
def test_AtomicDifferentialDense_pickle():
max_atoms = 23
atom_features = 100
tg = TensorGraph()
atom_feature = Feature(shape=(None, max_atoms, atom_features))
atom_numbers = Feature(shape=(None, max_atoms))
atomic_differential_dense = AtomicDifferentiatedDense(
max_atoms=23, out_channels=5, in_layers=[atom_feature, atom_numbers])
tg.add_output(atomic_differential_dense)
tg.set_loss(atomic_differential_dense)
tg.build()
tg.save()
def build_graph(self):
self.atom_numbers = Feature(shape=(None, self.max_atoms),
dtype=tf.int32)
self.atom_flags = Feature(shape=(None,
self.max_atoms * self.max_atoms))
self.atom_feats = Feature(shape=(None, self.max_atoms * 4))
reshaped_atom_flags = Reshape(in_layers=[self.atom_flags],
shape=(-1, self.max_atoms,
self.max_atoms))
reshaped_atom_feats = Reshape(in_layers=[self.atom_feats],
shape=(-1, self.max_atoms, 4))
previous_layer = ANIFeat(in_layers=reshaped_atom_feats,
max_atoms=self.max_atoms)
self.featurized = previous_layer
Hiddens = []
for n_hidden in self.layer_structures:
Hidden = AtomicDifferentiatedDense(
self.max_atoms,
n_hidden,
self.atom_number_cases,
activation=self.activation_fn,
in_layers=[previous_layer, self.atom_numbers])
Hiddens.append(Hidden)
previous_layer = Hiddens[-1]
regression = Dense(out_channels=1 * self.n_tasks,
activation_fn=None,
in_layers=[Hiddens[-1]])
output = BPGather(self.max_atoms,
in_layers=[regression, reshaped_atom_flags])
self.add_output(output)
label = Label(shape=(None, self.n_tasks, 1))
loss = ReduceSum(L2Loss(in_layers=[label, output]))
weights = Weights(shape=(None, self.n_tasks))
weighted_loss = WeightedError(in_layers=[loss, weights])
if self.exp_loss:
weighted_loss = Exp(in_layers=[weighted_loss])
self.set_loss(weighted_loss)
