Merge pull request #522 from peastman/fc (6959cf0f) · Commits · 钟慕尧 / deepchem

deepchem/models/init.py

+5 −2

Original line number	Diff line number	Diff line
		@@ -18,11 +18,14 @@ from deepchem.models.sequential import Sequential
		from deepchem.models.tensorflow_models.fcnet import TensorflowMultiTaskRegressor
		from deepchem.models.tensorflow_models.fcnet import TensorflowMultiTaskClassifier
		from deepchem.models.tensorflow_models.fcnet import TensorflowMultiTaskFitTransformRegressor
		from deepchem.models.tensorflow_models.fcnet import TensorGraphMultiTaskRegressor
		from deepchem.models.tensorflow_models.fcnet import TensorGraphMultiTaskClassifier
		from deepchem.models.tensorflow_models.fcnet import TensorGraphMultiTaskFitTransformRegressor
		from deepchem.models.tensorflow_models.robust_multitask import RobustMultitaskRegressor
		from deepchem.models.tensorflow_models.robust_multitask import RobustMultitaskClassifier
		from deepchem.models.tensorflow_models.lr import TensorflowLogisticRegression
		from deepchem.models.tensorflow_models.progressive_multitask import ProgressiveMultitaskRegressor
		from deepchem.models.tensorflow_models.progressive_joint import ProgressiveJointRegressor
		from deepchem.models.tensorflow_models.IRV import TensorflowMultiTaskIRVClassifier
		from deepchem.models.tensorgraph.tensor_graph import TensorGraph, MultiTaskTensorGraph
		from deepchem.models.tensorgraph.tensor_graph import TensorGraph
		from deepchem.models.tensorgraph.models.graph_models import WeaveTensorGraph, DTNNTensorGraph, DAGTensorGraph

deepchem/models/tensorflow_models/fcnet.py

+320 −0

Original line number	Diff line number	Diff line
		@@ -18,6 +18,326 @@ from deepchem.models.tensorflow_models import TensorflowClassifier
		from deepchem.models.tensorflow_models import TensorflowRegressor
		from deepchem.metrics import to_one_hot

		from deepchem.models.tensorgraph.tensor_graph import TensorGraph, TFWrapper
		from deepchem.models.tensorgraph.layers import Feature, Label, Weights, WeightedError, Dense, Dropout, WeightDecay, Reshape, SoftMaxCrossEntropy, L2Loss


		class TensorGraphMultiTaskClassifier(TensorGraph):

		def __init__(self,
		n_tasks,
		n_features,
		layer_sizes=[1000],
		weight_init_stddevs=[0.02],
		bias_init_consts=[1.0],
		weight_decay_penalty=0.0,
		weight_decay_penalty_type="l2",
		dropouts=[0.5],
		n_classes=2,
		**kwargs):
		"""Create a TensorGraphMultiTaskClassifier.

		In addition to the following arguments, this class also accepts all the keywork arguments
		from TensorGraph.

		Parameters
		----------
		n_tasks: int
		number of tasks
		n_features: int
		number of features
		layer_sizes: list
		the size of each dense layer in the network. The length of this list determines the number of layers.
		weight_init_stddevs: list
		the standard deviation of the distribution to use for weight initialization of each layer. The length
		of this list should equal len(layer_sizes).
		bias_init_consts: list
		the value to initialize the biases in each layer to. The length of this list should equal len(layer_sizes).
		weight_decay_penalty: float
		the magnitude of the weight decay penalty to use
		weight_decay_penalty_type: str
		the type of penalty to use for weight decay, either 'l1' or 'l2'
		dropouts: list
		the dropout probablity to use for each layer. The length of this list should equal len(layer_sizes).
		n_classes: int
		the number of classes
		"""
		super().__init__(mode='classification', **kwargs)
		self.n_tasks = n_tasks
		self.n_features = n_features
		self.n_classes = n_classes

		# Add the input features.

		mol_features = Feature(shape=(None, n_features))
		prev_layer = mol_features

		# Add the dense layers

		for size, weight_stddev, bias_const, dropout in zip(
		layer_sizes, weight_init_stddevs, bias_init_consts, dropouts):
		layer = Dense(
		in_layers=[prev_layer],
		out_channels=size,
		activation_fn=tf.nn.relu,
		weights_initializer=TFWrapper(
		tf.truncated_normal_initializer, stddev=weight_stddev),
		biases_initializer=TFWrapper(
		tf.constant_initializer, value=bias_const))
		if dropout > 0.0:
		layer = Dropout(dropout, in_layers=[layer])
		prev_layer = layer

		# Compute the loss function for each label.

		output = Reshape(
		shape=(-1, n_tasks, n_classes),
		in_layers=[
		Dense(in_layers=[prev_layer], out_channels=n_tasks * n_classes)
		])
		self.add_output(output)
		labels = Label(shape=(None, n_tasks, n_classes))
		weights = Weights(shape=(None, n_tasks))
		loss = Reshape(
		shape=(-1, n_tasks),
		in_layers=[SoftMaxCrossEntropy(in_layers=[labels, output])])
		weighted_loss = WeightedError(in_layers=[loss, weights])
		if weight_decay_penalty != 0.0:
		weighted_loss = WeightDecay(
		weight_decay_penalty,
		weight_decay_penalty_type,
		in_layers=[weighted_loss])
		self.set_loss(weighted_loss)

		def default_generator(self,
		dataset,
		epochs=1,
		predict=False,
		pad_batches=True):
		for epoch in range(epochs):
		for (X_b, y_b, w_b, ids_b) in dataset.iterbatches(
		batch_size=self.batch_size,
		deterministic=True,
		pad_batches=pad_batches):
		feed_dict = dict()
		if y_b is not None and not predict:
		feed_dict[self.labels[0]] = to_one_hot(
		y_b.flatten(), self.n_classes).reshape(-1, self.n_tasks,
		self.n_classes)
		if X_b is not None:
		feed_dict[self.features[0]] = X_b
		if w_b is not None and not predict:
		feed_dict[self.task_weights[0]] = w_b
		yield feed_dict


		class TensorGraphMultiTaskRegressor(TensorGraph):

		def __init__(self,
		n_tasks,
		n_features,
		layer_sizes=[1000],
		weight_init_stddevs=[0.02, 0.02],
		bias_init_consts=[1.0, 1.0],
		weight_decay_penalty=0.0,
		weight_decay_penalty_type="l2",
		dropouts=[0.5],
		**kwargs):
		"""Create a TensorGraphMultiTaskRegressor.

		In addition to the following arguments, this class also accepts all the keywork arguments
		from TensorGraph.

		Parameters
		----------
		n_tasks: int
		number of tasks
		n_features: int
		number of features
		layer_sizes: list
		the size of each dense layer in the network. The length of this list determines the number of layers.
		weight_init_stddevs: list
		the standard deviation of the distribution to use for weight initialization of each layer. The length
		of this list should equal len(layer_sizes)+1. The final element corresponds to the output layer.
		bias_init_consts: list
		the value to initialize the biases in each layer to. The length of this list should equal len(layer_sizes)+1.
		The final element corresponds to the output layer.
		weight_decay_penalty: float
		the magnitude of the weight decay penalty to use
		weight_decay_penalty_type: str
		the type of penalty to use for weight decay, either 'l1' or 'l2'
		dropouts: list
		the dropout probablity to use for each layer. The length of this list should equal len(layer_sizes).
		"""
		super().__init__(mode='regression', **kwargs)
		self.n_tasks = n_tasks
		self.n_features = n_features

		# Add the input features.

		mol_features = Feature(shape=(None, n_features))
		prev_layer = mol_features

		# Add the dense layers

		for size, weight_stddev, bias_const, dropout in zip(
		layer_sizes, weight_init_stddevs, bias_init_consts, dropouts):
		layer = Dense(
		in_layers=[prev_layer],
		out_channels=size,
		activation_fn=tf.nn.relu,
		weights_initializer=TFWrapper(
		tf.truncated_normal_initializer, stddev=weight_stddev),
		biases_initializer=TFWrapper(
		tf.constant_initializer, value=bias_const))
		if dropout > 0.0:
		layer = Dropout(dropout, in_layers=[layer])
		prev_layer = layer

		# Compute the loss function for each label.

		output = Reshape(
		shape=(-1, n_tasks, 1),
		in_layers=[
		Dense(
		in_layers=[prev_layer],
		out_channels=n_tasks,
		weights_initializer=TFWrapper(
		tf.truncated_normal_initializer,
		stddev=weight_init_stddevs[-1]),
		biases_initializer=TFWrapper(
		tf.constant_initializer, value=bias_init_consts[-1]))
		])
		self.add_output(output)
		labels = Label(shape=(None, n_tasks, 1))
		weights = Weights(shape=(None, n_tasks))
		loss = Reshape(
		shape=(-1, n_tasks), in_layers=[L2Loss(in_layers=[labels, output])])
		weighted_loss = WeightedError(in_layers=[loss, weights])
		if weight_decay_penalty != 0.0:
		weighted_loss = WeightDecay(
		weight_decay_penalty,
		weight_decay_penalty_type,
		in_layers=[weighted_loss])
		self.set_loss(weighted_loss)

		def default_generator(self,
		dataset,
		epochs=1,
		predict=False,
		pad_batches=True):
		for epoch in range(epochs):
		for (X_b, y_b, w_b, ids_b) in dataset.iterbatches(
		batch_size=self.batch_size,
		deterministic=True,
		pad_batches=pad_batches):
		feed_dict = dict()
		if y_b is not None and not predict:
		feed_dict[self.labels[0]] = y_b.reshape(-1, self.n_tasks, 1)
		if X_b is not None:
		feed_dict[self.features[0]] = X_b
		if w_b is not None and not predict:
		feed_dict[self.task_weights[0]] = w_b
		yield feed_dict


		class TensorGraphMultiTaskFitTransformRegressor(TensorGraphMultiTaskRegressor):
		"""Implements a TensorGraphMultiTaskRegressor that performs on-the-fly transformation during fit/predict.

		Example:

		>>> n_samples = 10
		>>> n_features = 3
		>>> n_tasks = 1
		>>> ids = np.arange(n_samples)
		>>> X = np.random.rand(n_samples, n_features, n_features)
		>>> y = np.zeros((n_samples, n_tasks))
		>>> w = np.ones((n_samples, n_tasks))
		>>> dataset = dc.data.NumpyDataset(X, y, w, ids)
		>>> fit_transformers = [dc.trans.CoulombFitTransformer(dataset)]
		>>> model = dc.models.TensorflowMultiTaskFitTransformRegressor(n_tasks, [n_features, n_features],
		... dropouts=[0.], learning_rate=0.003, weight_init_stddevs=[np.sqrt(6)/np.sqrt(1000)],
		... batch_size=n_samples, fit_transformers=fit_transformers, n_evals=1)
		n_features after fit_transform: 12
		"""

		def __init__(self,
		n_tasks,
		n_features,
		fit_transformers=[],
		n_evals=1,
		batch_size=50,
		**kwargs):
		"""Create a TensorGraphMultiTaskFitTransformRegressor.

		In addition to the following arguments, this class also accepts all the keywork arguments
		from TensorGraphMultiTaskRegressor.

		Parameters
		----------
		n_tasks: int
		number of tasks
		n_features: list or int
		number of features
		fit_transformers: list
		List of dc.trans.FitTransformer objects
		n_evals: int
		Number of evalations per example at predict time
		"""
		self.fit_transformers = fit_transformers
		self.n_evals = n_evals

		# Run fit transformers on dummy dataset to determine n_features after transformation

		if isinstance(n_features, list):
		X_b = np.ones([batch_size] + n_features)
		elif isinstance(n_features, int):
		X_b = np.ones([batch_size, n_features])
		else:
		raise ValueError("n_features should be list or int")
		for transformer in fit_transformers:
		X_b = transformer.X_transform(X_b)
		n_features = X_b.shape[1]
		print("n_features after fit_transform: %d" % int(n_features))
		super().__init__(n_tasks, n_features, batch_size=batch_size, **kwargs)

		def default_generator(self,
		dataset,
		epochs=1,
		predict=False,
		pad_batches=True):
		for epoch in range(epochs):
		for (X_b, y_b, w_b, ids_b) in dataset.iterbatches(
		batch_size=self.batch_size,
		deterministic=True,
		pad_batches=pad_batches):
		feed_dict = dict()
		if y_b is not None and not predict:
		feed_dict[self.labels[0]] = y_b.reshape(-1, self.n_tasks, 1)
		if X_b is not None:
		if not predict:
		for transformer in self.fit_transformers:
		X_b = transformer.X_transform(X_b)
		feed_dict[self.features[0]] = X_b
		if w_b is not None and not predict:
		feed_dict[self.task_weights[0]] = w_b
		yield feed_dict

		def predict_proba_on_generator(self, generator, transformers=[]):

		def transform_generator():
		for feed_dict in generator:
		X = feed_dict[self.features[0]]
		for i in range(self.n_evals):
		X_t = X
		for transformer in self.fit_transformers:
		X_t = transformer.X_transform(X_t)
		feed_dict[self.features[0]] = X_t
		yield feed_dict

		return super().predict_proba_on_generator(transform_generator(),
		transformers)


		class TensorflowMultiTaskClassifier(TensorflowClassifier):
		"""Implements an icml model as configured in a model_config.proto."""

deepchem/models/tensorgraph/init.py

+1 −1

Original line number	Diff line number	Diff line
		from deepchem.models.tensorgraph.tensor_graph import TensorGraphfrom deepchem.models.tensorgraph import models
		No newline at end of file
		from deepchem.models.tensorgraph.tensor_graph import TensorGraph, TFWrapperfrom deepchem.models.tensorgraph import models
		No newline at end of file

deepchem/models/tensorgraph/graph_layers.py

+9 −9

Original line number	Diff line number	Diff line
		@@ -25,7 +25,7 @@ class Combine_AP(Layer):
		def __init__(self, **kwargs):
		super(Combine_AP, self).__init__(**kwargs)

		def create_tensor(self, in_layers=None):
		def create_tensor(self, in_layers=None, **kwargs):
		if in_layers is None:
		in_layers = self.in_layers
		in_layers = convert_to_layers(in_layers)
		@@ -39,7 +39,7 @@ class Separate_AP(Layer):
		def __init__(self, **kwargs):
		super(Separate_AP, self).__init__(**kwargs)

		def create_tensor(self, in_layers=None):
		def create_tensor(self, in_layers=None, **kwargs):
		if in_layers is None:
		in_layers = self.in_layers
		in_layers = convert_to_layers(in_layers)
		@@ -147,7 +147,7 @@ class WeaveLayer(Layer):
		self.trainable_weights.extend(
		[self.W_AP, self.b_AP, self.W_PP, self.b_PP, self.W_P, self.b_P])

		def create_tensor(self, in_layers=None):
		def create_tensor(self, in_layers=None, **kwargs):
		""" description and explanation refer to deepchem.nn.WeaveLayer
		parent layers: [atom_features, pair_features], pair_split, atom_to_pair
		"""
		@@ -241,7 +241,7 @@ class WeaveGather(Layer):
		else:
		self.trainable_weights = None

		def create_tensor(self, in_layers=None):
		def create_tensor(self, in_layers=None, **kwargs):
		""" description and explanation refer to deepchem.nn.WeaveGather
		parent layers: atom_features, atom_split
		"""
		@@ -312,7 +312,7 @@ class DTNNEmbedding(Layer):
		[self.periodic_table_length, self.n_embedding])
		self.trainable_weights = [self.embedding_list]

		def create_tensor(self, in_layers=None):
		def create_tensor(self, in_layers=None, **kwargs):
		"""description and explanation refer to deepchem.nn.DTNNEmbedding
		parent layers: atom_number
		"""
		@@ -375,7 +375,7 @@ class DTNNStep(Layer):
		self.W_cf, self.W_df, self.W_fc, self.b_cf, self.b_df
		]

		def create_tensor(self, in_layers=None):
		def create_tensor(self, in_layers=None, **kwargs):
		"""description and explanation refer to deepchem.nn.DTNNStep
		parent layers: atom_features, distance, distance_membership_i, distance_membership_j
		"""
		@@ -461,7 +461,7 @@ class DTNNGather(Layer):

		self.trainable_weights = self.W_list + self.b_list

		def create_tensor(self, in_layers=None):
		def create_tensor(self, in_layers=None, **kwargs):
		"""description and explanation refer to deepchem.nn.DTNNGather
		parent layers: atom_features, atom_membership
		"""
		@@ -548,7 +548,7 @@ class DAGLayer(Layer):

		self.trainable_weights = self.W_list + self.b_list

		def create_tensor(self, in_layers=None):
		def create_tensor(self, in_layers=None, **kwargs):
		"""description and explanation refer to deepchem.nn.DAGLayer
		parent layers: atom_features, parents, calculation_orders, calculation_masks, n_atoms
		"""
		@@ -686,7 +686,7 @@ class DAGGather(Layer):

		self.trainable_weights = self.W_list + self.b_list

		def create_tensor(self, in_layers=None):
		def create_tensor(self, in_layers=None, **kwargs):
		"""description and explanation refer to deepchem.nn.DAGGather
		parent layers: atom_features, membership
		"""

deepchem/models/tensorgraph/layers.py

+82 −34

File changed.

Preview size limit exceeded, changes collapsed.

Admin message