Test (dfdf3afc) · Commits · 钟慕尧 / deepchem

deepchem/models/tensorgraph/symmetry_functions.py

+40 −35

Original line number	Diff line number	Diff line
		@@ -21,7 +21,6 @@ from deepchem.metrics import to_one_hot


		class DistanceMatrix(Layer):

		def __init__(self, max_atoms, **kwargs):
		"""
		Parameters
		@@ -52,7 +51,6 @@ class DistanceMatrix(Layer):


		class DistanceCutoff(Layer):

		def __init__(self, max_atoms, cutoff=6 / 0.52917721092, **kwargs):
		"""
		Parameters
		@@ -353,7 +351,6 @@ class AngularSymmetryMod(Layer):


		class BPFeatureMerge(Layer):

		def __init__(self, max_atoms, **kwargs):
		self.max_atoms = max_atoms
		super(BPFeatureMerge, self).__init__(**kwargs)
		@@ -375,7 +372,6 @@ class BPFeatureMerge(Layer):


		class BPGather(Layer):

		def __init__(self, max_atoms, **kwargs):
		self.max_atoms = max_atoms
		super(BPGather, self).__init__(**kwargs)
		@@ -403,8 +399,8 @@ class AtomicDifferentiatedDense(Layer):
		init='glorot_uniform',
		activation='relu',
		**kwargs):
		self.init = initializations.get(init) # Set weight initialization
		self.activation = activations.get(activation) # Get activations
		self.init = init # Set weight initialization
		self.activation = activation # Get activations
		self.max_atoms = max_atoms
		self.out_channels = out_channels
		self.atom_number_cases = atom_number_cases
		@@ -413,6 +409,8 @@ class AtomicDifferentiatedDense(Layer):

		def create_tensor(self, in_layers=None, set_tensors=True, **kwargs):
		""" Generate Radial Symmetry Function """
		init_fn = initializations.get(self.init) # Set weight initialization
		activation_fn = activations.get(self.activation)
		if in_layers is None:
		in_layers = self.in_layers
		in_layers = convert_to_layers(in_layers)
		@@ -420,13 +418,12 @@ class AtomicDifferentiatedDense(Layer):
		inputs = in_layers[0].out_tensor
		atom_numbers = in_layers[1].out_tensor
		in_channels = inputs.get_shape().as_list()[-1]
		self.W = self.init(
		self.W = init_fn(
		[len(self.atom_number_cases), in_channels, self.out_channels])

		self.b = model_ops.zeros((len(self.atom_number_cases), self.out_channels))
		outputs = []
		for i, atom_case in enumerate(self.atom_number_cases):

		# optimization to allow for tensorcontraction/broadcasted mmul
		# using a reshape trick. Note that the np and tf matmul behavior
		# differs when dealing with broadcasts
		@@ -439,7 +436,7 @@ class AtomicDifferentiatedDense(Layer):
		ak = tf.shape(a)[2]
		bl = tf.shape(b)[1]

		output = self.activation(
		output = activation_fn(
		tf.reshape(tf.matmul(tf.reshape(a, [ai * aj, ak]), b), [ai, aj, bl]) +
		self.b[i, :])

		@@ -448,3 +445,11 @@ class AtomicDifferentiatedDense(Layer):
		self.out_channels))
		outputs.append(output)
		self.out_tensor = tf.add_n(outputs)

		def none_tensors(self):
		w, b, out_tensor = self.W, self.b, self.out_tensor
		self.W, self.b, self.out_tensor = None, None, None
		return w, b, out_tensor

		def set_tensors(self, tensor):
		self.W, self.b, self.out_tensor = tensor

examples/qm7/qm7_ANI.py

+13 −3

Original line number	Diff line number	Diff line
		@@ -6,8 +6,12 @@ from __future__ import division
		from __future__ import unicode_literals

		import numpy as np

		from models import TensorGraph

		np.random.seed(123)
		import tensorflow as tf

		tf.set_random_seed(123)
		import deepchem as dc

		@@ -52,9 +56,15 @@ model.fit(train_dataset, nb_epoch=300, checkpoint_interval=100)
		print("Evaluating model")
		train_scores = model.evaluate(train_dataset, metric, transformers)
		valid_scores = model.evaluate(valid_dataset, metric, transformers)
		model.save()

		model = TensorGraph.load_from_dir(model.model_dir)
		train_scores2 = model.evaluate(train_dataset, metric, transformers)
		valid_scores2 = model.evaluate(valid_dataset, metric, transformers)
		print("Train scores")
		print(train_scores)
		print(train_scores2)

		print("Validation scores")
		print(valid_scores)
		print(valid_scores2)

Admin message