cleaning up (9af9659c) · Commits · 钟慕尧 / deepchem

deepchem/models/tensorgraph/graph_layers.py

+9 −5

Original line number	Diff line number	Diff line
		@@ -470,8 +470,9 @@ class DTNNGather(Layer):

		def __init__(self,
		n_embedding=30,
		n_outputs=1,
		layer_sizes=[15],
		n_outputs=100,
		layer_sizes=[100],
		output_activation=True,
		init='glorot_uniform',
		activation='tanh',
		**kwargs):
		@@ -492,6 +493,7 @@ class DTNNGather(Layer):
		self.n_embedding = n_embedding
		self.n_outputs = n_outputs
		self.layer_sizes = layer_sizes
		self.output_activation = output_activation
		self.init = initializations.get(init) # Set weight initialization
		self.activation = activations.get(activation) # Get activations

		@@ -530,6 +532,8 @@ class DTNNGather(Layer):
		output = tf.matmul(output, W) + self.b_list[i]
		output = self.activation(output)
		output = tf.matmul(output, self.W_list[-1]) + self.b_list[-1]
		if self.output_activation:
		output = self.activation(output)
		output = tf.segment_sum(output, atom_membership)
		out_tensor = output
		if set_tensors:

+8 −9

Original line number	Diff line number	Diff line
		@@ -1102,7 +1102,9 @@ class BatchNorm(Layer):
		self.out_tensor = out_tensor
		return out_tensor


		class BatchNormalization(Layer):

		def __init__(self,
		epsilon=1e-5,
		axis=-1,
		@@ -1125,13 +1127,9 @@ class BatchNormalization(Layer):
		def build(self, input_shape):
		shape = (input_shape[self.axis],)
		self.gamma = self.add_weight(
		shape,
		initializer=self.gamma_init,
		name='{}_gamma'.format(self.name))
		shape, initializer=self.gamma_init, name='{}_gamma'.format(self.name))
		self.beta = self.add_weight(
		shape,
		initializer=self.beta_init,
		name='{}_beta'.format(self.name))
		shape, initializer=self.beta_init, name='{}_beta'.format(self.name))

		def create_tensor(self, in_layers=None, set_tensors=True, **kwargs):
		inputs = self._get_input_tensors(in_layers)
		@@ -1139,7 +1137,8 @@ class BatchNormalization(Layer):
		input_shape = model_ops.int_shape(x)
		self.build(input_shape)
		m = model_ops.mean(x, axis=-1, keepdims=True)
		std = model_ops.sqrt(model_ops.var(x, axis=-1, keepdims=True) + self.epsilon)
		std = model_ops.sqrt(
		model_ops.var(x, axis=-1, keepdims=True) + self.epsilon)
		x_normed = (x - m) / (std + self.epsilon)
		x_normed = self.gamma * x_normed + self.beta
		out_tensor = x_normed

+4 −2

Original line number	Diff line number	Diff line
		@@ -163,7 +163,7 @@ class WeaveTensorGraph(TensorGraph):

		feed_dict[self.atom_features] = np.concatenate(atom_feat, axis=0)
		feed_dict[self.pair_features] = np.concatenate(pair_feat, axis=0)
		feed_dict[self.pair_split] = pair_split
		feed_dict[self.pair_split] = np.array(pair_split)
		feed_dict[self.atom_split] = np.array(atom_split)
		feed_dict[self.atom_to_pair] = np.concatenate(atom_to_pair, axis=0)
		yield feed_dict
		@@ -178,6 +178,7 @@ class DTNNTensorGraph(TensorGraph):
		n_distance=100,
		distance_min=-1,
		distance_max=18,
		output_activation=True,
		**kwargs):
		"""
		Parameters
		@@ -207,6 +208,7 @@ class DTNNTensorGraph(TensorGraph):
		self.steps = np.array(
		[distance_min + i * self.step_size for i in range(n_distance)])
		self.steps = np.expand_dims(self.steps, 0)
		self.output_activation = output_activation
		super(DTNNTensorGraph, self).__init__(**kwargs)
		assert self.mode == "regression"
		self.build_graph()
		@@ -241,6 +243,7 @@ class DTNNTensorGraph(TensorGraph):
		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 = []
		@@ -258,7 +261,6 @@ class DTNNTensorGraph(TensorGraph):
		loss = WeightedError(in_layers=[all_cost, self.weights])
		self.set_loss(loss)


		def default_generator(self,
		dataset,
		epochs=1,

+8 −3

Original line number	Diff line number	Diff line
		@@ -19,7 +19,12 @@ from deepchem.models.tensorgraph.symmetry_functions import DistanceMatrix, \

		class BPSymmetryFunctionRegression(TensorGraph):

		def __init__(self, n_tasks, max_atoms, n_feat=96, layer_structures=[128, 64], **kwargs):
		def __init__(self,
		n_tasks,
		max_atoms,
		n_feat=96,
		layer_structures=[128, 64],
		**kwargs):
		"""
		Parameters
		----------
		@@ -69,7 +74,6 @@ class BPSymmetryFunctionRegression(TensorGraph):
		loss = WeightedError(in_layers=[all_cost, self.weights])
		self.set_loss(loss)


		def default_generator(self,
		dataset,
		epochs=1,
		@@ -96,6 +100,7 @@ class BPSymmetryFunctionRegression(TensorGraph):
		feed_dict[self.atom_feats] = np.array(X_b[:, :, 1:], dtype=float)
		yield feed_dict


		class ANIRegression(TensorGraph):

		def __init__(self,

+9 −8

Original line number	Diff line number	Diff line
		@@ -420,14 +420,15 @@ class AtomicDifferentiatedDense(Layer):
		inputs = in_layers[0].out_tensor
		atom_numbers = in_layers[1].out_tensor
		in_channels = inputs.get_shape().as_list()[-1]
		self.W = self.init([len(self.atom_number_cases), in_channels, self.out_channels])
		self.W = self.init(
		[len(self.atom_number_cases), in_channels, self.out_channels])
		self.b = model_ops.zeros((len(self.atom_number_cases), self.out_channels))
		outputs = []
		for i, atom_case in enumerate(self.atom_number_cases):
		output = self.activation(tf.tensordot(inputs, self.W[i, :, :], [[2], [0]]) + self.b[i, :])
		output = self.activation(
		tf.tensordot(inputs, self.W[i, :, :], [[2], [0]]) + self.b[i, :])
		mask = 1 - tf.to_float(tf.cast(atom_numbers - atom_case, tf.bool))
		output = tf.reshape(output * tf.expand_dims(mask, 2), (-1, self.max_atoms, self.out_channels))
		output = tf.reshape(output * tf.expand_dims(mask, 2), (-1, self.max_atoms,
		self.out_channels))
		outputs.append(output)
		self.out_tensor = tf.add_n(outputs)