Tweaking (61854bd3) · Commits · 钟慕尧 / deepchem

deepchem/models/tensorflow_models/fcnet.py

+58 −7

Original line number	Diff line number	Diff line
		@@ -14,6 +14,7 @@ import collections
		import deepchem as dc
		from deepchem.nn import model_ops
		from deepchem.utils.save import log
		from deepchem.metrics import to_one_hot, from_one_hot
		from deepchem.models.tensorflow_models import TensorflowGraph
		from deepchem.models.tensorflow_models import TensorflowGraphModel
		from deepchem.models.tensorflow_models import TensorflowClassifier
		@@ -72,8 +73,7 @@ class TensorGraphMultiTaskClassifier(TensorGraph):
		n_classes: int
		the number of classes
		"""
		super(TensorGraphMultiTaskClassifier, self).__init__(
		mode='classification', **kwargs)
		super(TensorGraphMultiTaskClassifier, self).__init__(**kwargs)
		self.n_tasks = n_tasks
		self.n_features = n_features
		self.n_classes = n_classes
		@@ -150,6 +150,35 @@ class TensorGraphMultiTaskClassifier(TensorGraph):
		feed_dict[self.task_weights[0]] = w_b
		yield feed_dict

		def predict_proba(self, dataset, transformers=[], outputs=None):
		return self.run(dataset, transformers, outputs)


		def predict(self, dataset, transformers=[], outputs=None):
		"""
		Uses self to make predictions on provided Dataset object.

		Parameters
		----------
		dataset: dc.data.Dataset
		Dataset to make prediction on
		transformers: list
		List of dc.trans.Transformers.
		outputs: object
		If outputs is None, then will assume outputs = self.outputs[0] (single
		output). If outputs is a Layer/Tensor, then will evaluate and return as a
		single ndarray. If outputs is a list of Layers/Tensors, will return a list
		of ndarrays.

		Returns
		-------
		y_pred: numpy ndarray or list of numpy ndarrays
		"""
		# Results is of shape (n_samples, n_tasks, n_classes)
		results = self.run(dataset, transformers, outputs)
		# retval is of shape (n_samples, n_tasks)
		return np.argmax(retval, axis=2)


		class TensorGraphMultiTaskRegressor(TensorGraph):

		@@ -197,8 +226,7 @@ class TensorGraphMultiTaskRegressor(TensorGraph):
		len(layer_sizes). Alternatively this may be a single value instead of a list, in which case the
		same value is used for every layer.
		"""
		super(TensorGraphMultiTaskRegressor, self).__init__(
		mode='regression', **kwargs)
		super(TensorGraphMultiTaskRegressor, self).__init__(**kwargs)
		self.n_tasks = n_tasks
		self.n_features = n_features
		n_layers = len(layer_sizes)
		@@ -278,6 +306,29 @@ class TensorGraphMultiTaskRegressor(TensorGraph):
		feed_dict[self.task_weights[0]] = w_b
		yield feed_dict

		def predict(self, dataset, transformers=[], outputs=None):
		"""
		Uses self to make predictions on provided Dataset object.

		Parameters
		----------
		dataset: dc.data.Dataset
		Dataset to make prediction on
		transformers: list
		List of dc.trans.Transformers.
		outputs: object
		If outputs is None, then will assume outputs = self.outputs[0] (single
		output). If outputs is a Layer/Tensor, then will evaluate and return as a
		single ndarray. If outputs is a list of Layers/Tensors, will return a list
		of ndarrays.

		Returns
		-------
		y_pred: numpy ndarray or list of numpy ndarrays
		"""
		# Results is of shape (n_samples, n_tasks)
		return self.run(dataset, transformers, outputs)


		class TensorGraphMultiTaskFitTransformRegressor(TensorGraphMultiTaskRegressor):
		"""Implements a TensorGraphMultiTaskRegressor that performs on-the-fly transformation during fit/predict.
		@@ -362,7 +413,8 @@ class TensorGraphMultiTaskFitTransformRegressor(TensorGraphMultiTaskRegressor):
		feed_dict[self.task_weights[0]] = w_b
		yield feed_dict

		def predict_proba_on_generator(self, generator, transformers=[]):
		#def predict_proba_on_generator(self, generator, transformers=[]):
		def run_on_generator(self, generator, transformers=[], outputs=None):

		def transform_generator():
		for feed_dict in generator:
		@@ -375,8 +427,7 @@ class TensorGraphMultiTaskFitTransformRegressor(TensorGraphMultiTaskRegressor):
		yield feed_dict

		return super(TensorGraphMultiTaskFitTransformRegressor,
		self).predict_proba_on_generator(transform_generator(),
		transformers)
		self).run_on_generator(transform_generator(), transformers, output)


		class TensorflowMultiTaskClassifier(TensorflowClassifier):

deepchem/models/tensorgraph/tensor_graph.py

+6 −7

Original line number	Diff line number	Diff line
		@@ -28,7 +28,6 @@ class TensorGraph(Model):
		batch_size=100,
		random_seed=None,
		use_queue=True,
		mode="regression",
		graph=None,
		learning_rate=0.001,
		**kwargs):
		@@ -48,10 +47,6 @@ class TensorGraph(Model):
		queue in batches of self.batch_size in a separate thread from the
		thread training the model. You cannot use a queue when
		batches are not of consistent size
		mode: str
		"regression" or "classification". "classification" models on
		predict will do an argmax(axis=2) to determine the class of the
		prediction.
		graph: tensorflow.Graph
		the Graph in which to create Tensorflow objects. If None, a new Graph
		is created.
		@@ -287,7 +282,11 @@ class TensorGraph(Model):
		result = sess.run(out_tensors, feed_dict=feed_dict)
		result = undo_transforms(result, transformers)
		results.append(result)
		return np.concatenate(results, axis=0)
		if len(results) == 1:
		return results[0]
		else:
		return results
		#return np.concatenate(results, axis=0)

		# def bayesian_predict_on_batch(self, X, transformers=[], n_passes=4):
		# """
		@@ -361,7 +360,7 @@ class TensorGraph(Model):

		Returns
		-------
		y_pred: numpy ndarray or list of numpy ndarrays
		results: numpy ndarray or list of numpy ndarrays
		"""
		generator = self.default_generator(dataset, predict=True, pad_batches=False)
		return self.predict_on_generator(generator, transformers, outputs)

Admin message