fixing bugs (1e646c4e) · Commits · 钟慕尧 / deepchem

deepchem/models/init.py

+1 −1

Original line number	Diff line number	Diff line
		@@ -9,7 +9,7 @@ from deepchem.models.models import Model
		from deepchem.models.sklearn_models import SklearnModel
		from deepchem.models.tf_new_models.multitask_classifier import MultitaskGraphClassifier
		from deepchem.models.tf_new_models.multitask_regressor import MultitaskGraphRegressor
		from deepchem.models.tf_new_models.DTNN_regressor import DTNNRegressor
		from deepchem.models.tf_new_models.DTNN_regressor import DTNNGraphRegressor

		from deepchem.models.tf_new_models.support_classifier import SupportGraphClassifier
		from deepchem.models.multitask import SingletaskToMultitask

+4 −5

Original line number	Diff line number	Diff line
		@@ -666,8 +666,6 @@ class TestOverfit(test_util.TensorFlowTestCase):
		"""Test deep tensor neural net overfits tiny data."""
		np.random.seed(123)
		tf.set_random_seed(123)
		g = tf.Graph()
		sess = tf.Session(graph=g)

		# Load mini log-solubility dataset.
		input_file = os.path.join(self.current_dir, "example_DTNN.mat")
		@@ -688,11 +686,12 @@ class TestOverfit(test_util.TensorFlowTestCase):
		graph_model.add(dc.nn.DTNNStep())
		graph_model.add(dc.nn.DTNNGather(n_tasks=n_tasks))

		model = dc.models.DTNNRegressor(
		model = dc.models.DTNNGraphRegressor(
		graph_model,
		n_tasks=n_tasks,
		n_tasks,
		n_feat,
		batch_size=batch_size,
		learning_rate=1e-2,
		learning_rate=1e-3,
		learning_rate_decay_time=1000,
		optimizer_type="adam",
		beta1=.9,

0 → 100644

+28 −0

Original line number	Diff line number	Diff line
		import tensorflow as tf
		from deepchem.models.tf_new_models.multitask_regressor import MultitaskGraphRegressor


		class DTNNGraphRegressor(MultitaskGraphRegressor):

		def build(self):
		# Create target inputs
		self.label_placeholder = tf.placeholder(
		dtype='float32', shape=(None, self.n_tasks), name="label_placeholder")
		self.weight_placeholder = tf.placeholder(
		dtype='float32', shape=(None, self.n_tasks), name="weight_placholder")

		feat = self.model.return_outputs()
		feat_size = self.feat_dim
		outputs = []
		W_list = []
		b_list = []
		for task in range(self.n_tasks):
		W_list.append(
		tf.Variable(
		tf.truncated_normal([feat_size, 1], stddev=0.01),
		name='w',
		dtype=tf.float32))
		b_list.append(tf.Variable(tf.zeros([1]), name='b', dtype=tf.float32))
		outputs.append(
		tf.squeeze(tf.nn.xw_plus_b(feat, W_list[task], b_list[task])))
		return outputs

+0 −3

Original line number	Diff line number	Diff line
		@@ -128,9 +128,6 @@ class SequentialDTNNGraph(SequentialGraph):
		self.output = layer(self.output)
		self.layers.append(layer)

		def return_inputs(self):
		return self.graph_topology.get_atom_number_placeholders()


		class SequentialSupportGraph(object):
		"""An analog of Keras Sequential model for test/support models."""

+3 −3

Original line number	Diff line number	Diff line
		@@ -23,14 +23,14 @@ metric = [

		# Batch size of models
		batch_size = 50
		n_feat = [23, 23]
		graph_model = dc.nn.SequentialDTNNGraph(max_n_atoms=23, n_distance=100)
		graph_model.add(dc.nn.DTNNEmbedding(n_embedding=20))
		graph_model.add(dc.nn.DTNNStep(n_embedding=20, n_distance=100))
		graph_model.add(dc.nn.DTNNStep(n_embedding=20, n_distance=100))
		graph_model.add(dc.nn.DTNNGather(n_embedding=20))
		n_feat = 20

		model = dc.models.MultitaskGraphRegressor(
		model = dc.models.DTNNGraphRegressor(
		graph_model,
		len(tasks),
		n_feat,
		@@ -42,7 +42,7 @@ model = dc.models.MultitaskGraphRegressor(
		beta2=.999)

		# Fit trained model
		model.fit(train_dataset, nb_epoch=10)
		model.fit(train_dataset, nb_epoch=50)

		print("Evaluating model")
		train_scores = model.evaluate(train_dataset, metric, transformers)