Loading contrib/laplacian/petroskisuch.py 0 → 100644 +165 −0 Original line number Diff line number Diff line import collections import numpy as np import six import tensorflow as tf from deepchem.data import NumpyDataset from deepchem.feat.graph_features import ConvMolFeaturizer from deepchem.feat.mol_graphs import ConvMol from deepchem.metrics import to_one_hot from deepchem.models.tensorgraph.graph_layers import WeaveGather, \ DTNNEmbedding, DTNNStep, DTNNGather, DAGLayer, \ DAGGather, DTNNExtract, MessagePassing, SetGather from deepchem.models.tensorgraph.graph_layers import WeaveLayerFactory from deepchem.models.tensorgraph.layers import Dense, SoftMax, \ SoftMaxCrossEntropy, GraphConv, BatchNorm, \ GraphPool, GraphGather, WeightedError, Dropout, BatchNorm, Stack, Flatten, GraphCNN, GraphCNNPool from deepchem.models.tensorgraph.layers import L2Loss, Label, Weights, Feature from deepchem.models.tensorgraph.tensor_graph import TensorGraph from deepchem.trans import undo_transforms class PetroskiSuchModel(TensorGraph): """ Model from Robust Spatial Filtering with Graph Convolutional Neural Networks https://arxiv.org/abs/1703.00792 """ def __init__(self, n_tasks, max_atoms=200, dropout=0.0, mode="classification", **kwargs): """ Parameters ---------- n_tasks: int Number of tasks mode: str Either "classification" or "regression" """ self.n_tasks = n_tasks self.mode = mode self.max_atoms = max_atoms self.error_bars = True if 'error_bars' in kwargs and kwargs['error_bars'] else False self.dropout = dropout kwargs['use_queue'] = False super(PetroskiSuchModel, self).__init__(**kwargs) self.build_graph() def build_graph(self): self.vertex_features = Feature(shape=(None, self.max_atoms, 75)) self.adj_matrix = Feature(shape=(None, self.max_atoms, 1, self.max_atoms)) self.mask = Feature(shape=(None, self.max_atoms, 1)) gcnn1 = BatchNorm( GraphCNN( num_filters=64, in_layers=[self.vertex_features, self.adj_matrix, self.mask])) gcnn1 = Dropout(self.dropout, in_layers=gcnn1) gcnn2 = BatchNorm( GraphCNN(num_filters=64, in_layers=[gcnn1, self.adj_matrix, self.mask])) gcnn2 = Dropout(self.dropout, in_layers=gcnn2) gc_pool, adj_matrix = GraphCNNPool( num_vertices=32, in_layers=[gcnn2, self.adj_matrix, self.mask]) gc_pool = BatchNorm(gc_pool) gc_pool = Dropout(self.dropout, in_layers=gc_pool) gcnn3 = BatchNorm(GraphCNN(num_filters=32, in_layers=[gc_pool, adj_matrix])) gcnn3 = Dropout(self.dropout, in_layers=gcnn3) gc_pool2, adj_matrix2 = GraphCNNPool( num_vertices=8, in_layers=[gcnn3, adj_matrix]) gc_pool2 = BatchNorm(gc_pool2) gc_pool2 = Dropout(self.dropout, in_layers=gc_pool2) flattened = Flatten(in_layers=gc_pool2) readout = Dense( out_channels=256, activation_fn=tf.nn.relu, in_layers=flattened) costs = [] self.my_labels = [] for task in range(self.n_tasks): if self.mode == 'classification': classification = Dense( out_channels=2, activation_fn=None, in_layers=[readout]) softmax = SoftMax(in_layers=[classification]) self.add_output(softmax) label = Label(shape=(None, 2)) self.my_labels.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=[readout]) self.add_output(regression) label = Label(shape=(None, 1)) self.my_labels.append(label) cost = L2Loss(in_layers=[label, regression]) costs.append(cost) if self.mode == "classification": entropy = Stack(in_layers=costs, axis=-1) elif self.mode == "regression": entropy = Stack(in_layers=costs, axis=1) self.my_task_weights = Weights(shape=(None, self.n_tasks)) loss = WeightedError(in_layers=[entropy, self.my_task_weights]) self.set_loss(loss) def default_generator(self, dataset, epochs=1, predict=False, deterministic=True, pad_batches=True): for epoch in range(epochs): if not predict: print('Starting epoch %i' % epoch) for ind, (X_b, y_b, w_b, ids_b) in enumerate( dataset.iterbatches( self.batch_size, pad_batches=True, deterministic=deterministic)): d = {} for index, label in enumerate(self.my_labels): if self.mode == 'classification': d[label] = to_one_hot(y_b[:, index]) if self.mode == 'regression': d[label] = np.expand_dims(y_b[:, index], -1) d[self.my_task_weights] = w_b d[self.adj_matrix] = np.expand_dims(np.array([x[0] for x in X_b]), -2) d[self.vertex_features] = np.array([x[1] for x in X_b]) mask = np.zeros(shape=(self.batch_size, self.max_atoms, 1)) for i in range(self.batch_size): mask_size = X_b[i][2] mask[i][:mask_size][0] = 1 d[self.mask] = mask yield d def predict_proba_on_generator(self, generator, transformers=[]): if not self.built: self.build() with self._get_tf("Graph").as_default(): out_tensors = [x.out_tensor for x in self.outputs] results = [] for feed_dict in generator: feed_dict = { self.layers[k.name].out_tensor: v for k, v in six.iteritems(feed_dict) } feed_dict[self._training_placeholder] = 1.0 ## result = np.array(self.session.run(out_tensors, feed_dict=feed_dict)) if len(result.shape) == 3: result = np.transpose(result, axes=[1, 0, 2]) if len(transformers) > 0: result = undo_transforms(result, transformers) results.append(result) return np.concatenate(results, axis=0) def evaluate(self, dataset, metrics, transformers=[], per_task_metrics=False): if not self.built: self.build() return self.evaluate_generator( self.default_generator(dataset, predict=True), metrics, labels=self.my_labels, weights=[self.my_task_weights], per_task_metrics=per_task_metrics) deepchem/models/tensorgraph/graph_layers.py +25 −13 Original line number Diff line number Diff line Loading @@ -581,16 +581,18 @@ class DAGLayer(Layer): Number of features listed per atom. max_atoms: int, optional Maximum number of atoms in molecules. layer_sizes: list of int, optional(default=[1000]) Structure of hidden layer(s) layer_sizes: list of int, optional(default=[100]) List of hidden layer size(s): length of this list represents the number of hidden layers, and each element is the width of corresponding hidden layer. init: str, optional Weight initialization for filters. activation: str, optional Activation function applied Activation function applied. dropout: float, optional Dropout probability, not supported here Dropout probability in hidden layer(s). batch_size: int, optional number of molecules in a batch number of molecules in a batch. """ super(DAGLayer, self).__init__(**kwargs) Loading Loading @@ -683,7 +685,8 @@ class DAGLayer(Layer): # DAGgraph_step maps from batch_inputs to a batch of graph_features # of shape: (batch_size*max_atoms) * n_graph_features # representing the graph features of target atoms in each graph batch_outputs = self.DAGgraph_step(batch_inputs, self.W_list, self.b_list) batch_outputs = self.DAGgraph_step(batch_inputs, self.W_list, self.b_list, **kwargs) # index for targe atoms target_index = tf.stack([tf.range(n_atoms), parents[:, count, 0]], axis=1) Loading @@ -698,11 +701,14 @@ class DAGLayer(Layer): self.out_tensor = out_tensor return out_tensor def DAGgraph_step(self, batch_inputs, W_list, b_list): def DAGgraph_step(self, batch_inputs, W_list, b_list, **kwargs): outputs = batch_inputs for idw, W in enumerate(W_list): outputs = tf.nn.xw_plus_b(outputs, W, b_list[idw]) outputs = self.activation(outputs) training = kwargs['training'] if 'training' in kwargs else 1.0 if not self.dropout is None: outputs = tf.nn.dropout(outputs, 1.0 - self.dropout * training) return outputs def none_tensors(self): Loading Loading @@ -733,19 +739,21 @@ class DAGGather(Layer): Parameters ---------- n_graph_feat: int, optional Number of features for each atom Number of features for each atom. n_outputs: int, optional Number of features for each molecule. max_atoms: int, optional Maximum number of atoms in molecules. layer_sizes: list of int, optional Structure of hidden layer(s) List of hidden layer size(s): length of this list represents the number of hidden layers, and each element is the width of corresponding hidden layer. init: str, optional Weight initialization for filters. activation: str, optional Activation function applied Activation function applied. dropout: float, optional Dropout probability, not supported Dropout probability in the hidden layer(s). """ super(DAGGather, self).__init__(**kwargs) Loading Loading @@ -794,18 +802,22 @@ class DAGGather(Layer): # Extract atom_features graph_features = tf.segment_sum(atom_features, membership) # sum all graph outputs outputs = self.DAGgraph_step(graph_features, self.W_list, self.b_list) outputs = self.DAGgraph_step(graph_features, self.W_list, self.b_list, **kwargs) out_tensor = outputs if set_tensors: self.variables = self.trainable_weights self.out_tensor = out_tensor return out_tensor def DAGgraph_step(self, batch_inputs, W_list, b_list): def DAGgraph_step(self, batch_inputs, W_list, b_list, **kwargs): outputs = batch_inputs for idw, W in enumerate(W_list): outputs = tf.nn.xw_plus_b(outputs, W, b_list[idw]) outputs = self.activation(outputs) training = kwargs['training'] if 'training' in kwargs else 1.0 if not self.dropout is None: outputs = tf.nn.dropout(outputs, 1.0 - self.dropout * training) return outputs def none_tensors(self): Loading deepchem/models/tensorgraph/models/graph_models.py +23 −160 Original line number Diff line number Diff line Loading @@ -391,22 +391,33 @@ class DAGModel(TensorGraph): n_atom_feat=75, n_graph_feat=30, n_outputs=30, layer_sizes=[100], layer_sizes_gather=[100], dropout=None, mode="classification", **kwargs): """ Parameters ---------- n_tasks: int Number of tasks Number of tasks. max_atoms: int, optional Maximum number of atoms in a molecule, should be defined based on dataset Maximum number of atoms in a molecule, should be defined based on dataset. n_atom_feat: int, optional Number of features per atom. n_graph_feat: int, optional Number of features for atom in the graph Number of features for atom in the graph. n_outputs: int, optional Number of features for each molecule mode: str Number of features for each molecule. layer_sizes: list of int, optional List of hidden layer size(s) in the propagation step: length of this list represents the number of hidden layers, and each element is the width of corresponding hidden layer. layer_sizes_gather: list of int, optional List of hidden layer size(s) in the gather step. dropout: None or float, optional Dropout probability, applied after each propagation step and gather step. mode: str, optional Either "classification" or "regression" for type of model. """ self.n_tasks = n_tasks Loading @@ -414,6 +425,9 @@ class DAGModel(TensorGraph): self.n_atom_feat = n_atom_feat self.n_graph_feat = n_graph_feat self.n_outputs = n_outputs self.layer_sizes = layer_sizes self.layer_sizes_gather = layer_sizes_gather self.dropout = dropout self.mode = mode super(DAGModel, self).__init__(**kwargs) self.build_graph() Loading @@ -435,6 +449,8 @@ class DAGModel(TensorGraph): n_graph_feat=self.n_graph_feat, n_atom_feat=self.n_atom_feat, max_atoms=self.max_atoms, layer_sizes=self.layer_sizes, dropout=self.dropout, batch_size=self.batch_size, in_layers=[ self.atom_features, self.parents, self.calculation_orders, Loading @@ -444,6 +460,8 @@ class DAGModel(TensorGraph): n_graph_feat=self.n_graph_feat, n_outputs=self.n_outputs, max_atoms=self.max_atoms, layer_sizes=self.layer_sizes_gather, dropout=self.dropout, in_layers=[dag_layer1, self.membership]) costs = [] Loading Loading @@ -544,150 +562,6 @@ class DAGModel(TensorGraph): return out class PetroskiSuchModel(TensorGraph): """ Model from Robust Spatial Filtering with Graph Convolutional Neural Networks https://arxiv.org/abs/1703.00792 """ def __init__(self, n_tasks, max_atoms=200, dropout=0.0, mode="classification", **kwargs): """ Parameters ---------- n_tasks: int Number of tasks mode: str Either "classification" or "regression" """ self.n_tasks = n_tasks self.mode = mode self.max_atoms = max_atoms self.dropout = dropout kwargs['use_queue'] = False super(PetroskiSuchModel, self).__init__(**kwargs) self.build_graph() def build_graph(self): self.vertex_features = Feature(shape=(None, self.max_atoms, 75)) self.adj_matrix = Feature(shape=(None, self.max_atoms, 1, self.max_atoms)) self.mask = Feature(shape=(None, self.max_atoms, 1)) gcnn1 = BatchNorm( GraphCNN( num_filters=64, in_layers=[self.vertex_features, self.adj_matrix, self.mask])) gcnn1 = Dropout(self.dropout, in_layers=gcnn1) gcnn2 = BatchNorm( GraphCNN(num_filters=64, in_layers=[gcnn1, self.adj_matrix, self.mask])) gcnn2 = Dropout(self.dropout, in_layers=gcnn2) gc_pool, adj_matrix = GraphCNNPool( num_vertices=32, in_layers=[gcnn2, self.adj_matrix, self.mask]) gc_pool = BatchNorm(gc_pool) gc_pool = Dropout(self.dropout, in_layers=gc_pool) gcnn3 = BatchNorm(GraphCNN(num_filters=32, in_layers=[gc_pool, adj_matrix])) gcnn3 = Dropout(self.dropout, in_layers=gcnn3) gc_pool2, adj_matrix2 = GraphCNNPool( num_vertices=8, in_layers=[gcnn3, adj_matrix]) gc_pool2 = BatchNorm(gc_pool2) gc_pool2 = Dropout(self.dropout, in_layers=gc_pool2) flattened = Flatten(in_layers=gc_pool2) readout = Dense( out_channels=256, activation_fn=tf.nn.relu, in_layers=flattened) costs = [] self.my_labels = [] for task in range(self.n_tasks): if self.mode == 'classification': classification = Dense( out_channels=2, activation_fn=None, in_layers=[readout]) softmax = SoftMax(in_layers=[classification]) self.add_output(softmax) label = Label(shape=(None, 2)) self.my_labels.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=[readout]) self.add_output(regression) label = Label(shape=(None, 1)) self.my_labels.append(label) cost = L2Loss(in_layers=[label, regression]) costs.append(cost) if self.mode == "classification": entropy = Stack(in_layers=costs, axis=-1) elif self.mode == "regression": entropy = Stack(in_layers=costs, axis=1) self.my_task_weights = Weights(shape=(None, self.n_tasks)) loss = WeightedError(in_layers=[entropy, self.my_task_weights]) self.set_loss(loss) def default_generator(self, dataset, epochs=1, predict=False, deterministic=True, pad_batches=True): for epoch in range(epochs): if not predict: print('Starting epoch %i' % epoch) for ind, (X_b, y_b, w_b, ids_b) in enumerate( dataset.iterbatches( self.batch_size, pad_batches=True, deterministic=deterministic)): d = {} for index, label in enumerate(self.my_labels): if self.mode == 'classification': d[label] = to_one_hot(y_b[:, index]) if self.mode == 'regression': d[label] = np.expand_dims(y_b[:, index], -1) d[self.my_task_weights] = w_b d[self.adj_matrix] = np.expand_dims(np.array([x[0] for x in X_b]), -2) d[self.vertex_features] = np.array([x[1] for x in X_b]) mask = np.zeros(shape=(self.batch_size, self.max_atoms, 1)) for i in range(self.batch_size): mask_size = X_b[i][2] mask[i][:mask_size][0] = 1 d[self.mask] = mask yield d def predict_proba_on_generator(self, generator, transformers=[]): if not self.built: self.build() with self._get_tf("Graph").as_default(): out_tensors = [x.out_tensor for x in self.outputs] results = [] for feed_dict in generator: feed_dict = { self.layers[k.name].out_tensor: v for k, v in six.iteritems(feed_dict) } feed_dict[self._training_placeholder] = 1.0 ## result = np.array(self.session.run(out_tensors, feed_dict=feed_dict)) if len(result.shape) == 3: result = np.transpose(result, axes=[1, 0, 2]) if len(transformers) > 0: result = undo_transforms(result, transformers) results.append(result) return np.concatenate(results, axis=0) def evaluate(self, dataset, metrics, transformers=[], per_task_metrics=False): if not self.built: self.build() return self.evaluate_generator( self.default_generator(dataset, predict=True), metrics, labels=self.my_labels, weights=[self.my_task_weights], per_task_metrics=per_task_metrics) class GraphConvModel(TensorGraph): def __init__(self, Loading Loading @@ -1112,17 +986,6 @@ class DAGTensorGraph(DAGModel): super(DAGModel, self).__init__(*args, **kwargs) class PetroskiSuchTensorGraph(PetroskiSuchModel): def __init__(self, *args, **kwargs): warnings.warn( TENSORGRAPH_DEPRECATION.format("PetroskiSuchTensorGraph", "PetroskiSuchModel"), FutureWarning) super(PetroskiSuchModel, self).__init__(*args, **kwargs) class MPNNTensorGraph(MPNNModel): def __init__(self, *args, **kwargs): Loading deepchem/models/tensorgraph/models/test_graph_models.py +5 −1 Original line number Diff line number Diff line Loading @@ -6,7 +6,7 @@ import deepchem from deepchem.data import NumpyDataset from deepchem.models import GraphConvModel from deepchem.models import TensorGraph from deepchem.molnet.load_function.delaney_datasets import load_delaney from deepchem.molnet import load_bace_classification, load_delaney from deepchem.models.tensorgraph.layers import ReduceSum, L2Loss from deepchem.models import WeaveModel from deepchem.feat import ConvMolFeaturizer Loading @@ -19,7 +19,11 @@ class TestGraphModels(unittest.TestCase): featurizer='GraphConv', num_tasks=2): data_points = 10 if mode == 'classification': tasks, all_dataset, transformers = load_bace_classification(featurizer) else: tasks, all_dataset, transformers = load_delaney(featurizer) train, valid, test = all_dataset for i in range(1, num_tasks): tasks.append("random_task") Loading examples/delaney/delaney_graph_conv.py +1 −1 Original line number Diff line number Diff line Loading @@ -7,7 +7,7 @@ from __future__ import unicode_literals import numpy as np from models import GraphConvModel from deepchem.models import GraphConvModel np.random.seed(123) import tensorflow as tf Loading Loading
contrib/laplacian/petroskisuch.py 0 → 100644 +165 −0 Original line number Diff line number Diff line import collections import numpy as np import six import tensorflow as tf from deepchem.data import NumpyDataset from deepchem.feat.graph_features import ConvMolFeaturizer from deepchem.feat.mol_graphs import ConvMol from deepchem.metrics import to_one_hot from deepchem.models.tensorgraph.graph_layers import WeaveGather, \ DTNNEmbedding, DTNNStep, DTNNGather, DAGLayer, \ DAGGather, DTNNExtract, MessagePassing, SetGather from deepchem.models.tensorgraph.graph_layers import WeaveLayerFactory from deepchem.models.tensorgraph.layers import Dense, SoftMax, \ SoftMaxCrossEntropy, GraphConv, BatchNorm, \ GraphPool, GraphGather, WeightedError, Dropout, BatchNorm, Stack, Flatten, GraphCNN, GraphCNNPool from deepchem.models.tensorgraph.layers import L2Loss, Label, Weights, Feature from deepchem.models.tensorgraph.tensor_graph import TensorGraph from deepchem.trans import undo_transforms class PetroskiSuchModel(TensorGraph): """ Model from Robust Spatial Filtering with Graph Convolutional Neural Networks https://arxiv.org/abs/1703.00792 """ def __init__(self, n_tasks, max_atoms=200, dropout=0.0, mode="classification", **kwargs): """ Parameters ---------- n_tasks: int Number of tasks mode: str Either "classification" or "regression" """ self.n_tasks = n_tasks self.mode = mode self.max_atoms = max_atoms self.error_bars = True if 'error_bars' in kwargs and kwargs['error_bars'] else False self.dropout = dropout kwargs['use_queue'] = False super(PetroskiSuchModel, self).__init__(**kwargs) self.build_graph() def build_graph(self): self.vertex_features = Feature(shape=(None, self.max_atoms, 75)) self.adj_matrix = Feature(shape=(None, self.max_atoms, 1, self.max_atoms)) self.mask = Feature(shape=(None, self.max_atoms, 1)) gcnn1 = BatchNorm( GraphCNN( num_filters=64, in_layers=[self.vertex_features, self.adj_matrix, self.mask])) gcnn1 = Dropout(self.dropout, in_layers=gcnn1) gcnn2 = BatchNorm( GraphCNN(num_filters=64, in_layers=[gcnn1, self.adj_matrix, self.mask])) gcnn2 = Dropout(self.dropout, in_layers=gcnn2) gc_pool, adj_matrix = GraphCNNPool( num_vertices=32, in_layers=[gcnn2, self.adj_matrix, self.mask]) gc_pool = BatchNorm(gc_pool) gc_pool = Dropout(self.dropout, in_layers=gc_pool) gcnn3 = BatchNorm(GraphCNN(num_filters=32, in_layers=[gc_pool, adj_matrix])) gcnn3 = Dropout(self.dropout, in_layers=gcnn3) gc_pool2, adj_matrix2 = GraphCNNPool( num_vertices=8, in_layers=[gcnn3, adj_matrix]) gc_pool2 = BatchNorm(gc_pool2) gc_pool2 = Dropout(self.dropout, in_layers=gc_pool2) flattened = Flatten(in_layers=gc_pool2) readout = Dense( out_channels=256, activation_fn=tf.nn.relu, in_layers=flattened) costs = [] self.my_labels = [] for task in range(self.n_tasks): if self.mode == 'classification': classification = Dense( out_channels=2, activation_fn=None, in_layers=[readout]) softmax = SoftMax(in_layers=[classification]) self.add_output(softmax) label = Label(shape=(None, 2)) self.my_labels.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=[readout]) self.add_output(regression) label = Label(shape=(None, 1)) self.my_labels.append(label) cost = L2Loss(in_layers=[label, regression]) costs.append(cost) if self.mode == "classification": entropy = Stack(in_layers=costs, axis=-1) elif self.mode == "regression": entropy = Stack(in_layers=costs, axis=1) self.my_task_weights = Weights(shape=(None, self.n_tasks)) loss = WeightedError(in_layers=[entropy, self.my_task_weights]) self.set_loss(loss) def default_generator(self, dataset, epochs=1, predict=False, deterministic=True, pad_batches=True): for epoch in range(epochs): if not predict: print('Starting epoch %i' % epoch) for ind, (X_b, y_b, w_b, ids_b) in enumerate( dataset.iterbatches( self.batch_size, pad_batches=True, deterministic=deterministic)): d = {} for index, label in enumerate(self.my_labels): if self.mode == 'classification': d[label] = to_one_hot(y_b[:, index]) if self.mode == 'regression': d[label] = np.expand_dims(y_b[:, index], -1) d[self.my_task_weights] = w_b d[self.adj_matrix] = np.expand_dims(np.array([x[0] for x in X_b]), -2) d[self.vertex_features] = np.array([x[1] for x in X_b]) mask = np.zeros(shape=(self.batch_size, self.max_atoms, 1)) for i in range(self.batch_size): mask_size = X_b[i][2] mask[i][:mask_size][0] = 1 d[self.mask] = mask yield d def predict_proba_on_generator(self, generator, transformers=[]): if not self.built: self.build() with self._get_tf("Graph").as_default(): out_tensors = [x.out_tensor for x in self.outputs] results = [] for feed_dict in generator: feed_dict = { self.layers[k.name].out_tensor: v for k, v in six.iteritems(feed_dict) } feed_dict[self._training_placeholder] = 1.0 ## result = np.array(self.session.run(out_tensors, feed_dict=feed_dict)) if len(result.shape) == 3: result = np.transpose(result, axes=[1, 0, 2]) if len(transformers) > 0: result = undo_transforms(result, transformers) results.append(result) return np.concatenate(results, axis=0) def evaluate(self, dataset, metrics, transformers=[], per_task_metrics=False): if not self.built: self.build() return self.evaluate_generator( self.default_generator(dataset, predict=True), metrics, labels=self.my_labels, weights=[self.my_task_weights], per_task_metrics=per_task_metrics)
deepchem/models/tensorgraph/graph_layers.py +25 −13 Original line number Diff line number Diff line Loading @@ -581,16 +581,18 @@ class DAGLayer(Layer): Number of features listed per atom. max_atoms: int, optional Maximum number of atoms in molecules. layer_sizes: list of int, optional(default=[1000]) Structure of hidden layer(s) layer_sizes: list of int, optional(default=[100]) List of hidden layer size(s): length of this list represents the number of hidden layers, and each element is the width of corresponding hidden layer. init: str, optional Weight initialization for filters. activation: str, optional Activation function applied Activation function applied. dropout: float, optional Dropout probability, not supported here Dropout probability in hidden layer(s). batch_size: int, optional number of molecules in a batch number of molecules in a batch. """ super(DAGLayer, self).__init__(**kwargs) Loading Loading @@ -683,7 +685,8 @@ class DAGLayer(Layer): # DAGgraph_step maps from batch_inputs to a batch of graph_features # of shape: (batch_size*max_atoms) * n_graph_features # representing the graph features of target atoms in each graph batch_outputs = self.DAGgraph_step(batch_inputs, self.W_list, self.b_list) batch_outputs = self.DAGgraph_step(batch_inputs, self.W_list, self.b_list, **kwargs) # index for targe atoms target_index = tf.stack([tf.range(n_atoms), parents[:, count, 0]], axis=1) Loading @@ -698,11 +701,14 @@ class DAGLayer(Layer): self.out_tensor = out_tensor return out_tensor def DAGgraph_step(self, batch_inputs, W_list, b_list): def DAGgraph_step(self, batch_inputs, W_list, b_list, **kwargs): outputs = batch_inputs for idw, W in enumerate(W_list): outputs = tf.nn.xw_plus_b(outputs, W, b_list[idw]) outputs = self.activation(outputs) training = kwargs['training'] if 'training' in kwargs else 1.0 if not self.dropout is None: outputs = tf.nn.dropout(outputs, 1.0 - self.dropout * training) return outputs def none_tensors(self): Loading Loading @@ -733,19 +739,21 @@ class DAGGather(Layer): Parameters ---------- n_graph_feat: int, optional Number of features for each atom Number of features for each atom. n_outputs: int, optional Number of features for each molecule. max_atoms: int, optional Maximum number of atoms in molecules. layer_sizes: list of int, optional Structure of hidden layer(s) List of hidden layer size(s): length of this list represents the number of hidden layers, and each element is the width of corresponding hidden layer. init: str, optional Weight initialization for filters. activation: str, optional Activation function applied Activation function applied. dropout: float, optional Dropout probability, not supported Dropout probability in the hidden layer(s). """ super(DAGGather, self).__init__(**kwargs) Loading Loading @@ -794,18 +802,22 @@ class DAGGather(Layer): # Extract atom_features graph_features = tf.segment_sum(atom_features, membership) # sum all graph outputs outputs = self.DAGgraph_step(graph_features, self.W_list, self.b_list) outputs = self.DAGgraph_step(graph_features, self.W_list, self.b_list, **kwargs) out_tensor = outputs if set_tensors: self.variables = self.trainable_weights self.out_tensor = out_tensor return out_tensor def DAGgraph_step(self, batch_inputs, W_list, b_list): def DAGgraph_step(self, batch_inputs, W_list, b_list, **kwargs): outputs = batch_inputs for idw, W in enumerate(W_list): outputs = tf.nn.xw_plus_b(outputs, W, b_list[idw]) outputs = self.activation(outputs) training = kwargs['training'] if 'training' in kwargs else 1.0 if not self.dropout is None: outputs = tf.nn.dropout(outputs, 1.0 - self.dropout * training) return outputs def none_tensors(self): Loading
deepchem/models/tensorgraph/models/graph_models.py +23 −160 Original line number Diff line number Diff line Loading @@ -391,22 +391,33 @@ class DAGModel(TensorGraph): n_atom_feat=75, n_graph_feat=30, n_outputs=30, layer_sizes=[100], layer_sizes_gather=[100], dropout=None, mode="classification", **kwargs): """ Parameters ---------- n_tasks: int Number of tasks Number of tasks. max_atoms: int, optional Maximum number of atoms in a molecule, should be defined based on dataset Maximum number of atoms in a molecule, should be defined based on dataset. n_atom_feat: int, optional Number of features per atom. n_graph_feat: int, optional Number of features for atom in the graph Number of features for atom in the graph. n_outputs: int, optional Number of features for each molecule mode: str Number of features for each molecule. layer_sizes: list of int, optional List of hidden layer size(s) in the propagation step: length of this list represents the number of hidden layers, and each element is the width of corresponding hidden layer. layer_sizes_gather: list of int, optional List of hidden layer size(s) in the gather step. dropout: None or float, optional Dropout probability, applied after each propagation step and gather step. mode: str, optional Either "classification" or "regression" for type of model. """ self.n_tasks = n_tasks Loading @@ -414,6 +425,9 @@ class DAGModel(TensorGraph): self.n_atom_feat = n_atom_feat self.n_graph_feat = n_graph_feat self.n_outputs = n_outputs self.layer_sizes = layer_sizes self.layer_sizes_gather = layer_sizes_gather self.dropout = dropout self.mode = mode super(DAGModel, self).__init__(**kwargs) self.build_graph() Loading @@ -435,6 +449,8 @@ class DAGModel(TensorGraph): n_graph_feat=self.n_graph_feat, n_atom_feat=self.n_atom_feat, max_atoms=self.max_atoms, layer_sizes=self.layer_sizes, dropout=self.dropout, batch_size=self.batch_size, in_layers=[ self.atom_features, self.parents, self.calculation_orders, Loading @@ -444,6 +460,8 @@ class DAGModel(TensorGraph): n_graph_feat=self.n_graph_feat, n_outputs=self.n_outputs, max_atoms=self.max_atoms, layer_sizes=self.layer_sizes_gather, dropout=self.dropout, in_layers=[dag_layer1, self.membership]) costs = [] Loading Loading @@ -544,150 +562,6 @@ class DAGModel(TensorGraph): return out class PetroskiSuchModel(TensorGraph): """ Model from Robust Spatial Filtering with Graph Convolutional Neural Networks https://arxiv.org/abs/1703.00792 """ def __init__(self, n_tasks, max_atoms=200, dropout=0.0, mode="classification", **kwargs): """ Parameters ---------- n_tasks: int Number of tasks mode: str Either "classification" or "regression" """ self.n_tasks = n_tasks self.mode = mode self.max_atoms = max_atoms self.dropout = dropout kwargs['use_queue'] = False super(PetroskiSuchModel, self).__init__(**kwargs) self.build_graph() def build_graph(self): self.vertex_features = Feature(shape=(None, self.max_atoms, 75)) self.adj_matrix = Feature(shape=(None, self.max_atoms, 1, self.max_atoms)) self.mask = Feature(shape=(None, self.max_atoms, 1)) gcnn1 = BatchNorm( GraphCNN( num_filters=64, in_layers=[self.vertex_features, self.adj_matrix, self.mask])) gcnn1 = Dropout(self.dropout, in_layers=gcnn1) gcnn2 = BatchNorm( GraphCNN(num_filters=64, in_layers=[gcnn1, self.adj_matrix, self.mask])) gcnn2 = Dropout(self.dropout, in_layers=gcnn2) gc_pool, adj_matrix = GraphCNNPool( num_vertices=32, in_layers=[gcnn2, self.adj_matrix, self.mask]) gc_pool = BatchNorm(gc_pool) gc_pool = Dropout(self.dropout, in_layers=gc_pool) gcnn3 = BatchNorm(GraphCNN(num_filters=32, in_layers=[gc_pool, adj_matrix])) gcnn3 = Dropout(self.dropout, in_layers=gcnn3) gc_pool2, adj_matrix2 = GraphCNNPool( num_vertices=8, in_layers=[gcnn3, adj_matrix]) gc_pool2 = BatchNorm(gc_pool2) gc_pool2 = Dropout(self.dropout, in_layers=gc_pool2) flattened = Flatten(in_layers=gc_pool2) readout = Dense( out_channels=256, activation_fn=tf.nn.relu, in_layers=flattened) costs = [] self.my_labels = [] for task in range(self.n_tasks): if self.mode == 'classification': classification = Dense( out_channels=2, activation_fn=None, in_layers=[readout]) softmax = SoftMax(in_layers=[classification]) self.add_output(softmax) label = Label(shape=(None, 2)) self.my_labels.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=[readout]) self.add_output(regression) label = Label(shape=(None, 1)) self.my_labels.append(label) cost = L2Loss(in_layers=[label, regression]) costs.append(cost) if self.mode == "classification": entropy = Stack(in_layers=costs, axis=-1) elif self.mode == "regression": entropy = Stack(in_layers=costs, axis=1) self.my_task_weights = Weights(shape=(None, self.n_tasks)) loss = WeightedError(in_layers=[entropy, self.my_task_weights]) self.set_loss(loss) def default_generator(self, dataset, epochs=1, predict=False, deterministic=True, pad_batches=True): for epoch in range(epochs): if not predict: print('Starting epoch %i' % epoch) for ind, (X_b, y_b, w_b, ids_b) in enumerate( dataset.iterbatches( self.batch_size, pad_batches=True, deterministic=deterministic)): d = {} for index, label in enumerate(self.my_labels): if self.mode == 'classification': d[label] = to_one_hot(y_b[:, index]) if self.mode == 'regression': d[label] = np.expand_dims(y_b[:, index], -1) d[self.my_task_weights] = w_b d[self.adj_matrix] = np.expand_dims(np.array([x[0] for x in X_b]), -2) d[self.vertex_features] = np.array([x[1] for x in X_b]) mask = np.zeros(shape=(self.batch_size, self.max_atoms, 1)) for i in range(self.batch_size): mask_size = X_b[i][2] mask[i][:mask_size][0] = 1 d[self.mask] = mask yield d def predict_proba_on_generator(self, generator, transformers=[]): if not self.built: self.build() with self._get_tf("Graph").as_default(): out_tensors = [x.out_tensor for x in self.outputs] results = [] for feed_dict in generator: feed_dict = { self.layers[k.name].out_tensor: v for k, v in six.iteritems(feed_dict) } feed_dict[self._training_placeholder] = 1.0 ## result = np.array(self.session.run(out_tensors, feed_dict=feed_dict)) if len(result.shape) == 3: result = np.transpose(result, axes=[1, 0, 2]) if len(transformers) > 0: result = undo_transforms(result, transformers) results.append(result) return np.concatenate(results, axis=0) def evaluate(self, dataset, metrics, transformers=[], per_task_metrics=False): if not self.built: self.build() return self.evaluate_generator( self.default_generator(dataset, predict=True), metrics, labels=self.my_labels, weights=[self.my_task_weights], per_task_metrics=per_task_metrics) class GraphConvModel(TensorGraph): def __init__(self, Loading Loading @@ -1112,17 +986,6 @@ class DAGTensorGraph(DAGModel): super(DAGModel, self).__init__(*args, **kwargs) class PetroskiSuchTensorGraph(PetroskiSuchModel): def __init__(self, *args, **kwargs): warnings.warn( TENSORGRAPH_DEPRECATION.format("PetroskiSuchTensorGraph", "PetroskiSuchModel"), FutureWarning) super(PetroskiSuchModel, self).__init__(*args, **kwargs) class MPNNTensorGraph(MPNNModel): def __init__(self, *args, **kwargs): Loading
deepchem/models/tensorgraph/models/test_graph_models.py +5 −1 Original line number Diff line number Diff line Loading @@ -6,7 +6,7 @@ import deepchem from deepchem.data import NumpyDataset from deepchem.models import GraphConvModel from deepchem.models import TensorGraph from deepchem.molnet.load_function.delaney_datasets import load_delaney from deepchem.molnet import load_bace_classification, load_delaney from deepchem.models.tensorgraph.layers import ReduceSum, L2Loss from deepchem.models import WeaveModel from deepchem.feat import ConvMolFeaturizer Loading @@ -19,7 +19,11 @@ class TestGraphModels(unittest.TestCase): featurizer='GraphConv', num_tasks=2): data_points = 10 if mode == 'classification': tasks, all_dataset, transformers = load_bace_classification(featurizer) else: tasks, all_dataset, transformers = load_delaney(featurizer) train, valid, test = all_dataset for i in range(1, num_tasks): tasks.append("random_task") Loading
examples/delaney/delaney_graph_conv.py +1 −1 Original line number Diff line number Diff line Loading @@ -7,7 +7,7 @@ from __future__ import unicode_literals import numpy as np from models import GraphConvModel from deepchem.models import GraphConvModel np.random.seed(123) import tensorflow as tf Loading
