Some changes for vanilla graph-conv (1bebf769) · Commits · 钟慕尧 / deepchem

deepchem/models/init.py

+12 −2

Original line number	Diff line number	Diff line
		@@ -143,6 +143,12 @@ class Model(object):
		batch_size, deterministic=True, pad_batches=pad_batches):
		n_samples = len(X_batch)
		y_pred_batch = self.predict_on_batch(X_batch)
		################################################################### DEBUG
		#print("X_batch.shape, y_batch.shape")
		#print(X_batch.shape, y_batch.shape)
		#print("y_pred_batch.shape")
		#print(y_pred_batch.shape)
		################################################################### DEBUG
		y_pred_batch = np.reshape(y_pred_batch, (n_samples, n_tasks))
		y_pred_batch = undo_transforms(y_pred_batch, transformers)
		y_preds.append(y_pred_batch)
		@@ -151,6 +157,10 @@ class Model(object):
		# The iterbatches does padding with zero-weight examples on the last batch.
		# Remove padded examples.
		n_samples = len(dataset)
		################################################### DEBUG
		print("n_samples, y_pred.shape, (n_samples, n_tasks)")
		print(n_samples, y_pred.shape, (n_samples, n_tasks))
		################################################### DEBUG
		y_pred = np.reshape(y_pred, (n_samples, n_tasks))
		# Special case to handle singletasks.
		if n_tasks == 1:
		@@ -338,7 +348,7 @@ class Model(object):


		def predict_proba(self, dataset, transformers=[], batch_size=None,
		n_classes=2):
		n_classes=2, pad_batches=False):
		"""
		TODO: Do transformers even make sense here?

		@@ -348,7 +358,7 @@ class Model(object):
		y_preds = []
		n_tasks = self.get_num_tasks()
		for (X_batch, y_batch, w_batch, ids_batch) in dataset.iterbatches(
		batch_size, deterministic=True):
		batch_size, deterministic=True, pad_batches=pad_batches):
		y_pred_batch = self.predict_proba_on_batch(X_batch)
		batch_size = len(y_batch)
		y_pred_batch = np.reshape(y_pred_batch, (batch_size, n_tasks, n_classes))

deepchem/models/tensorflow_models/init.py

+4 −1

Original line number	Diff line number	Diff line
		@@ -187,7 +187,7 @@ class TensorflowGraphModel(object):
		gradient_costs = [] # costs used for gradient calculation

		with TensorflowGraph.shared_name_scope('costs', graph, name_scopes):
		for task in xrange(self.n_tasks):
		for task in range(self.n_tasks):
		task_str = str(task).zfill(len(str(self.n_tasks)))
		with TensorflowGraph.shared_name_scope(
		'cost_{}'.format(task_str), graph, name_scopes):
		@@ -555,6 +555,9 @@ class TensorflowClassifier(TensorflowGraphModel):
		(batch_outputs.shape,))
		outputs.append(batch_outputs)

		# TODO(rbharath): This is a bug! We're actually applying softmax twice.
		# I believe this is harmless since softmax of softmax doesn't change
		# properties, but I need to check this...
		# We apply softmax to predictions to get class probabilities.
		outputs = softmax(np.squeeze(np.hstack(outputs)))

Admin message