Code changes (55e8eacf) · Commits · 钟慕尧 / deepchem

deepchem/models/tf_new_models/graph_models.py

+10 −0

Original line number	Diff line number	Diff line
		@@ -39,6 +39,11 @@ class SequentialGraph(object):
		def add(self, layer):
		"""Adds a new layer to model."""
		with self.graph.as_default():
		############################################# DEBUG
		#print("start - add()")
		#print("self.output")
		#print(self.output)
		############################################# DEBUG
		# For graphical layers, add connectivity placeholders
		if type(layer).__name__ in ['GraphConv', 'GraphGather', 'GraphPool']:
		if (len(self.layers) > 0 and hasattr(self.layers[-1], "__name__")):
		@@ -49,6 +54,11 @@ class SequentialGraph(object):
		self.graph_topology.get_topology_placeholders())
		else:
		self.output = layer(self.output)
		############################################# DEBUG
		#print("end- add()")
		#print("self.output")
		#print(self.output)
		############################################# DEBUG

		# Add layer to the layer list
		self.layers.append(layer)

+5 −6

Original line number	Diff line number	Diff line
		@@ -133,18 +133,17 @@ class MultitaskGraphClassifier(Model):

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

		feat = self.model.return_outputs()
		################################################################ DEBUG
		#print("multitask classifier")
		#print("feat")
		#print(feat)
		################################################################ DEBUG
		output = model_ops.multitask_logits(feat, self.n_tasks)
		return output

+5 −2

Original line number	Diff line number	Diff line
		@@ -334,8 +334,11 @@ class Dense(Layer):
		output = model_ops.dot(x, self.W)
		if self.bias:
		output += self.b
		outputs = to_list(self.activation(output))
		return outputs
		################################################# DEBUG
		#outputs = to_list(self.activation(output))
		#return outputs
		return output
		################################################# DEBUG


		class Dropout(Layer):

+14 −11

Original line number	Diff line number	Diff line
		@@ -821,16 +821,16 @@ class LSTMStep(Layer):

		# Taken from Keras code [citation needed]
		####################################################### DEBUG
		print("x")
		print(x)
		print("self.W")
		print(self.W)
		print("h_tm1")
		print(h_tm1)
		print("self.U")
		print(self.U)
		print("self.b")
		print(self.b)
		#print("x")
		#print(x)
		#print("self.W")
		#print(self.W)
		#print("h_tm1")
		#print(h_tm1)
		#print("self.U")
		#print(self.U)
		#print("self.b")
		#print(self.b)
		####################################################### DEBUG
		z = model_ops.dot(x, self.W) + model_ops.dot(h_tm1, self.U) + self.b

		@@ -846,4 +846,7 @@ class LSTMStep(Layer):

		h = o * self.activation(c)

		return o, [h, c]
		####################################################### DEBUG
		#return o, [h, c]
		return h, [h, c]
		####################################################### DEBUG

+5 −18

Original line number	Diff line number	Diff line
		@@ -352,24 +352,6 @@ def epsilon():
		return 1e-7


		#def variable(value, dtype=tf.float32, name=None):
		# """Instantiates a variable and returns it.
		#
		# Parameters
		# ----------
		# value: Numpy array, initial value of the tensor.
		# dtype: Tensor type.
		# name: Optional name string for the tensor.
		#
		# Returns
		# -------
		# A variable instance (with Keras metadata included).
		# """
		# v = tf.Variable(value, dtype=dtype, name=name)
		# v._uses_learning_phase = False
		# return v


		def random_uniform_variable(shape,
		low,
		high,
		@@ -840,6 +822,11 @@ def fully_connected_layer(tensor,
		ValueError
		If input tensor is not 2D.
		"""
		###################################################### DEBUG
		#print("fully_connected_layer")
		#print("tensor")
		#print(tensor)
		###################################################### DEBUG
		if len(tensor.get_shape()) != 2:
		raise ValueError('Dense layer input must be 2D, not %dD' %
		len(tensor.get_shape()))