sluiceloss test and yapf (1b0d6dab) · Commits · 钟慕尧 / deepchem

deepchem/models/tensorgraph/layers.py

+51 −27

Original line number	Diff line number	Diff line
		@@ -115,8 +115,7 @@ class Layer(object):
		else:
		self.variable_scope = local_scope

		def set_summary(self, summary_op, summary_description=None,
		collections=None):
		def set_summary(self, summary_op, summary_description=None, collections=None):
		"""Annotates a tensor with a tf.summary operation
		Collects data from self.out_tensor by default but can be changed by setting
		self.tb_input to another tensor in create_tensor
		@@ -193,8 +192,7 @@ def convert_to_layers(in_layers):
		elif isinstance(in_layer, tf.Tensor):
		layers.append(TensorWrapper(in_layer))
		else:
		raise ValueError(
		"convert_to_layers must be invoked on layers or tensors")
		raise ValueError("convert_to_layers must be invoked on layers or tensors")
		return layers


		@@ -264,6 +262,7 @@ class Conv1D(Layer):


		class Dense(Layer):

		def __init__(
		self,
		out_channels,
		@@ -394,6 +393,7 @@ class Flatten(Layer):


		class Reshape(Layer):

		def __init__(self, shape, **kwargs):
		super(Reshape, self).__init__(**kwargs)
		self._new_shape = tuple(-1 if x is None else x for x in shape)
		@@ -424,6 +424,7 @@ class Reshape(Layer):


		class Squeeze(Layer):

		def __init__(self, in_layers=None, squeeze_dims=None, **kwargs):
		self.squeeze_dims = squeeze_dims
		super(Squeeze, self).__init__(in_layers, **kwargs)
		@@ -449,6 +450,7 @@ class Squeeze(Layer):


		class Transpose(Layer):

		def __init__(self, perm, **kwargs):
		super(Transpose, self).__init__(**kwargs)
		self.perm = perm
		@@ -469,6 +471,7 @@ class Transpose(Layer):


		class CombineMeanStd(Layer):

		def __init__(self, in_layers=None, **kwargs):
		super(CombineMeanStd, self).__init__(in_layers, **kwargs)
		try:
		@@ -490,6 +493,7 @@ class CombineMeanStd(Layer):


		class Repeat(Layer):

		def __init__(self, n_times, **kwargs):
		self.n_times = n_times
		super(Repeat, self).__init__(**kwargs)
		@@ -577,6 +581,7 @@ class GRU(Layer):


		class TimeSeriesDense(Layer):

		def __init__(self, out_channels, **kwargs):
		self.out_channels = out_channels
		super(TimeSeriesDense, self).__init__(**kwargs)
		@@ -596,6 +601,7 @@ class TimeSeriesDense(Layer):


		class Input(Layer):

		def __init__(self, shape, dtype=tf.float32, **kwargs):
		self._shape = tuple(shape)
		self.dtype = dtype
		@@ -625,21 +631,25 @@ class Input(Layer):


		class Feature(Input):

		def __init__(self, **kwargs):
		super(Feature, self).__init__(**kwargs)


		class Label(Input):

		def __init__(self, **kwargs):
		super(Label, self).__init__(**kwargs)


		class Weights(Input):

		def __init__(self, **kwargs):
		super(Weights, self).__init__(**kwargs)


		class L1Loss(Layer):

		def __init__(self, in_layers=None, **kwargs):
		super(L1Loss, self).__init__(in_layers, **kwargs)

		@@ -654,6 +664,7 @@ class L1Loss(Layer):


		class L2Loss(Layer):

		def __init__(self, in_layers=None, **kwargs):
		super(L2Loss, self).__init__(in_layers, **kwargs)
		try:
		@@ -677,6 +688,7 @@ class L2Loss(Layer):


		class SoftMax(Layer):

		def __init__(self, in_layers=None, **kwargs):
		super(SoftMax, self).__init__(in_layers, **kwargs)
		try:
		@@ -696,6 +708,7 @@ class SoftMax(Layer):


		class Concat(Layer):

		def __init__(self, in_layers=None, axis=1, **kwargs):
		self.axis = axis
		super(Concat, self).__init__(in_layers, **kwargs)
		@@ -720,6 +733,7 @@ class Concat(Layer):


		class Stack(Layer):

		def __init__(self, in_layers=None, axis=1, **kwargs):
		self.axis = axis
		super(Stack, self).__init__(in_layers, **kwargs)
		@@ -893,6 +907,7 @@ class InteratomicL2Distances(Layer):


		class SparseSoftMaxCrossEntropy(Layer):

		def __init__(self, in_layers=None, **kwargs):
		super(SparseSoftMaxCrossEntropy, self).__init__(in_layers, **kwargs)
		try:
		@@ -914,6 +929,7 @@ class SparseSoftMaxCrossEntropy(Layer):


		class SoftMaxCrossEntropy(Layer):

		def __init__(self, in_layers=None, **kwargs):
		super(SoftMaxCrossEntropy, self).__init__(in_layers, **kwargs)
		try:
		@@ -935,6 +951,7 @@ class SoftMaxCrossEntropy(Layer):


		class ReduceMean(Layer):

		def __init__(self, in_layers=None, axis=None, **kwargs):
		self.axis = axis
		super(ReduceMean, self).__init__(in_layers, **kwargs)
		@@ -963,6 +980,7 @@ class ReduceMean(Layer):


		class ToFloat(Layer):

		def __init__(self, in_layers=None, **kwargs):
		super(ToFloat, self).__init__(in_layers, **kwargs)
		try:
		@@ -981,6 +999,7 @@ class ToFloat(Layer):


		class ReduceSum(Layer):

		def __init__(self, in_layers=None, axis=None, **kwargs):
		self.axis = axis
		super(ReduceSum, self).__init__(in_layers, **kwargs)
		@@ -1009,6 +1028,7 @@ class ReduceSum(Layer):


		class ReduceSquareDifference(Layer):

		def __init__(self, in_layers=None, axis=None, **kwargs):
		self.axis = axis
		super(ReduceSquareDifference, self).__init__(in_layers, **kwargs)
		@@ -1112,6 +1132,7 @@ class Conv2D(Layer):


		class MaxPool(Layer):

		def __init__(self,
		ksize=[1, 2, 2, 1],
		strides=[1, 2, 2, 1],
		@@ -1132,10 +1153,7 @@ class MaxPool(Layer):
		inputs = self._get_input_tensors(in_layers)
		in_tensor = inputs[0]
		out_tensor = tf.nn.max_pool(
		in_tensor,
		ksize=self.ksize,
		strides=self.strides,
		padding=self.padding)
		in_tensor, ksize=self.ksize, strides=self.strides, padding=self.padding)
		if set_tensors:
		self.out_tensor = out_tensor
		return out_tensor
		@@ -1180,6 +1198,7 @@ class InputFifoQueue(Layer):


		class GraphConv(Layer):

		def __init__(self,
		out_channel,
		min_deg=0,
		@@ -1294,6 +1313,7 @@ class GraphConv(Layer):


		class GraphPool(Layer):

		def __init__(self, min_degree=0, max_degree=10, **kwargs):
		self.min_degree = min_degree
		self.max_degree = max_degree
		@@ -1342,6 +1362,7 @@ class GraphPool(Layer):


		class GraphGather(Layer):

		def __init__(self, batch_size, activation_fn=None, **kwargs):
		self.batch_size = batch_size
		self.activation_fn = activation_fn
		@@ -1515,9 +1536,9 @@ def _cosine_dist(x, y):
		y: tf.Tensor
		Input Tensor
		"""
		denom = (model_ops.sqrt(
		model_ops.sum(tf.square(x)) * model_ops.sum(tf.square(y))) +
		model_ops.epsilon())
		denom = (
		model_ops.sqrt(model_ops.sum(tf.square(x)) * model_ops.sum(tf.square(y)))
		+ model_ops.epsilon())
		return model_ops.dot(x, tf.transpose(y)) / denom


		@@ -1770,6 +1791,7 @@ class IterRefLSTMEmbedding(Layer):


		class BatchNorm(Layer):

		def __init__(self, in_layers=None, **kwargs):
		super(BatchNorm, self).__init__(in_layers, **kwargs)
		try:
		@@ -1788,6 +1810,7 @@ class BatchNorm(Layer):


		class BatchNormalization(Layer):

		def __init__(self,
		epsilon=1e-5,
		axis=-1,
		@@ -1831,6 +1854,7 @@ class BatchNormalization(Layer):


		class WeightedError(Layer):

		def __init__(self, in_layers=None, **kwargs):
		super(WeightedError, self).__init__(in_layers, **kwargs)
		self._shape = tuple()
		@@ -2063,9 +2087,7 @@ class NeighborList(Layer):
		# List of length N_atoms, each element of different length uniques_i
		nbrs = self.get_atoms_in_nbrs(coords, cells)
		padding = tf.fill((self.M_nbrs,), -1)
		padded_nbrs = [
		tf.concat([unique_nbrs, padding], 0) for unique_nbrs in nbrs
		]
		padded_nbrs = [tf.concat([unique_nbrs, padding], 0) for unique_nbrs in nbrs]

		# List of length N_atoms, each element of different length uniques_i
		# List of length N_atoms, each a tensor of shape
		@@ -2282,6 +2304,7 @@ class NeighborList(Layer):


		class Dropout(Layer):

		def __init__(self, dropout_prob, **kwargs):
		self.dropout_prob = dropout_prob
		super(Dropout, self).__init__(**kwargs)
		@@ -2328,14 +2351,15 @@ class WeightDecay(Layer):
		def create_tensor(self, in_layers=None, set_tensors=True, **kwargs):
		inputs = self._get_input_tensors(in_layers)
		parent_tensor = inputs[0]
		out_tensor = parent_tensor + model_ops.weight_decay(
		self.penalty_type, self.penalty)
		out_tensor = parent_tensor + model_ops.weight_decay(self.penalty_type,
		self.penalty)
		if set_tensors:
		self.out_tensor = out_tensor
		return out_tensor


		class AtomicConvolution(Layer):

		def __init__(self,
		atom_types=None,
		radial_params=list(),
		@@ -2563,8 +2587,7 @@ class AtomicConvolution(Layer):
		example_tensors = tf.unstack(X, axis=0)
		example_nbrs = tf.unstack(nbr_indices, axis=0)
		all_nbr_coords = []
		for example, (
		example_tensor,
		for example, (example_tensor,
		example_nbr) in enumerate(zip(example_tensors, example_nbrs)):
		nbr_coords = tf.gather(example_tensor, example_nbr)
		all_nbr_coords.append(nbr_coords)
		@@ -2744,6 +2767,7 @@ class SluiceLoss(Layer):
		subspaces.append(input_tensor[:, :subspace_size])
		subspaces.append(input_tensor[:, subspace_size:])
		product = tf.matmul(tf.transpose(subspaces[0]), subspaces[1])
		subspaces = []
		# calculate squared Frobenius norm
		temp.append(tf.reduce_sum(tf.pow(product, 2)))
		out_tensor = tf.reduce_sum(temp)

deepchem/models/tensorgraph/tests/test_layers.py

+14 −8

Original line number	Diff line number	Diff line
		@@ -49,7 +49,7 @@ from deepchem.models.tensorgraph.layers import IterRefLSTMEmbedding
		from deepchem.models.tensorgraph.layers import Stack
		from deepchem.models.tensorgraph.layers import AlphaShareLayer
		from deepchem.models.tensorgraph.layers import BetaShare
		#from deepchem.models.tensorgraph.layers import SluiceLoss
		from deepchem.models.tensorgraph.layers import SluiceLoss
		from deepchem.models.tensorgraph.layers import LayerSplitter

		import deepchem as dc
		@@ -131,8 +131,7 @@ class TestLayers(test_util.TensorFlowTestCase):
		dim = 2
		batch_size = 10
		mean_tensor = np.random.rand(dim)
		std_tensor = np.random.rand(
		1,)
		std_tensor = np.random.rand(1,)
		with self.test_session() as sess:
		mean_tensor = tf.convert_to_tensor(mean_tensor, dtype=tf.float32)
		std_tensor = tf.convert_to_tensor(std_tensor, dtype=tf.float32)
		@@ -470,8 +469,6 @@ class TestLayers(test_util.TensorFlowTestCase):
		assert test_out.shape == (n_test, n_feat)
		assert support_out.shape == (n_support, n_feat)



		# TODO(rbharath): This test should pass. Fix it!
		#def test_graph_pool(self):
		# """Test that GraphPool can be invoked."""
		@@ -618,7 +615,6 @@ class TestLayers(test_util.TensorFlowTestCase):
		result = sess.run(tf.gradients(v, v))
		assert result[0] == 1.0


		def test_alpha_share_layer(self):
		"""test that alpha share works correctly"""
		batch_size = 50
		@@ -667,3 +663,13 @@ class TestLayers(test_util.TensorFlowTestCase):
		sess.run(tf.global_variables_initializer())
		tf.assert_equal(input1, output1.eval())
		tf.assert_equal(input2, output2.eval())

		def test_sluice_loss(self):
		input1 = np.ones((3, 4))
		input2 = np.ones((2, 2))
		with self.test_session() as sess:
		input1 = tf.convert_to_tensor(input1, dtype=tf.float32)
		input2 = tf.convert_to_tensor(input2, dtype=tf.float32)
		output_tensor = SluiceLoss()(input1, input2)
		sess.run(tf.global_variables_initializer())
		assert output_tensor.eval() == 40.0

Admin message