yapf (e24b5c12) · Commits · 钟慕尧 / deepchem

deepchem/models/tensorgraph/layers.py

+86 −45

Original line number	Diff line number	Diff line
		@@ -71,6 +71,7 @@ class Layer(object):


		class Conv1DLayer(Layer):

		def __init__(self, width, out_channels, **kwargs):
		self.width = width
		self.out_channels = out_channels
		@@ -95,7 +96,11 @@ class Conv1DLayer(Layer):


		class Dense(Layer):
		def __init__(self, out_channels, activation_fn=None,

		def __init__(
		self,
		out_channels,
		activation_fn=None,
		biases_initializer=tf.zeros_initializer,
		weights_initializer=tf.contrib.layers.variance_scaling_initializer,
		time_series=False,
		@@ -141,12 +146,19 @@ class Dense(Layer):

		def shared(self, in_layers):
		self.reuse = True
		return Dense(self.out_channels, self.activation_fn, self.biases_initializer,
		self.weights_initializer, time_series=self.time_series,
		reuse=self.reuse, scope_name=self.scope_name, in_layers=in_layers)
		return Dense(
		self.out_channels,
		self.activation_fn,
		self.biases_initializer,
		self.weights_initializer,
		time_series=self.time_series,
		reuse=self.reuse,
		scope_name=self.scope_name,
		in_layers=in_layers)


		class Flatten(Layer):

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

		@@ -164,6 +176,7 @@ class Flatten(Layer):


		class Reshape(Layer):

		def __init__(self, shape, **kwargs):
		self.shape = shape
		super(Reshape, self).__init__(**kwargs)
		@@ -172,7 +185,9 @@ class Reshape(Layer):
		parent_tensor = self.in_layers[0].out_tensor
		self.out_tensor = tf.reshape(parent_tensor, self.shape)


		class Transpose(Layer):

		def __init__(self, out_shape, **kwargs):
		super(Transpose, self).__init__(**kwargs)
		self.out_shape = out_shape
		@@ -185,6 +200,7 @@ class Transpose(Layer):


		class CombineMeanStd(Layer):

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

		@@ -199,6 +215,7 @@ class CombineMeanStd(Layer):


		class Repeat(Layer):

		def __init__(self, n_times, **kwargs):
		self.n_times = n_times
		super(Repeat, self).__init__(**kwargs)
		@@ -213,6 +230,7 @@ class Repeat(Layer):


		class GRU(Layer):

		def __init__(self, n_hidden, out_channels, batch_size, **kwargs):
		self.n_hidden = n_hidden
		self.out_channels = out_channels
		@@ -235,6 +253,7 @@ class GRU(Layer):


		class TimeSeriesDense(Layer):

		def __init__(self, out_channels, **kwargs):
		super(TimeSeriesDense, self).__init__(**kwargs)

		@@ -248,6 +267,7 @@ class TimeSeriesDense(Layer):


		class Input(Layer):

		def __init__(self, shape, dtype=tf.float32, **kwargs):
		self.shape = shape
		self.dtype = dtype
		@@ -272,21 +292,25 @@ 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 L2LossLayer(Layer):

		def __init__(self, **kwargs):
		super(L2LossLayer, self).__init__(**kwargs)

		@@ -298,6 +322,7 @@ class L2LossLayer(Layer):


		class SoftMax(Layer):

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

		@@ -310,6 +335,7 @@ class SoftMax(Layer):


		class Concat(Layer):

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

		@@ -324,6 +350,7 @@ class Concat(Layer):


		class SoftMaxCrossEntropy(Layer):

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

		@@ -338,6 +365,7 @@ class SoftMaxCrossEntropy(Layer):


		class ReduceMean(Layer):

		def _create_tensor(self):
		if len(self.in_layers) > 1:
		out_tensors = [x.out_tensor for x in self.in_layers]
		@@ -350,6 +378,7 @@ class ReduceMean(Layer):


		class ReduceSquareDifference(Layer):

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

		@@ -361,6 +390,7 @@ class ReduceSquareDifference(Layer):


		class Conv2d(Layer):

		def __init__(self, num_outputs, kernel_size=5, **kwargs):
		self.num_outputs = num_outputs
		self.kernel_size = kernel_size
		@@ -379,6 +409,7 @@ class Conv2d(Layer):


		class MaxPool(Layer):

		def __init__(self,
		ksize=[1, 2, 2, 1],
		strides=[1, 2, 2, 1],
		@@ -433,6 +464,7 @@ class InputFifoQueue(Layer):


		class GraphConvLayer(Layer):

		def __init__(self,
		out_channel,
		min_deg=0,
		@@ -543,6 +575,7 @@ class GraphConvLayer(Layer):


		class GraphPoolLayer(Layer):

		def __init__(self, min_degree=0, max_degree=10, **kwargs):
		self.min_degree = min_degree
		self.max_degree = max_degree
		@@ -588,6 +621,7 @@ class GraphPoolLayer(Layer):


		class GraphGather(Layer):

		def __init__(self, batch_size, activation_fn=None, **kwargs):
		self.batch_size = batch_size
		self.activation_fn = activation_fn
		@@ -630,6 +664,7 @@ class GraphGather(Layer):


		class BatchNormLayer(Layer):

		def _create_tensor(self):
		parent_tensor = self.in_layers[0].out_tensor
		self.out_tensor = tf.layers.batch_normalization(parent_tensor)
		@@ -637,6 +672,7 @@ class BatchNormLayer(Layer):


		class WeightedError(Layer):

		def _create_tensor(self):
		entropy, weights = self.in_layers[0], self.in_layers[1]
		self.out_tensor = tf.reduce_sum(entropy.out_tensor * weights.out_tensor)
		@@ -644,7 +680,12 @@ class WeightedError(Layer):


		class AtomicConvolution(Layer):
		def __init__(self, atom_types=None, radial_params=list(), boxsize=None, **kwargs):

		def __init__(self,
		atom_types=None,
		radial_params=list(),
		boxsize=None,
		**kwargs):
		"""Atomic convoluation layer

		N = max_num_atoms, M = max_num_neighbors, B = batch_size, d = num_features

deepchem/models/tensorgraph/tensor_graph.py

+26 −25

Original line number	Diff line number	Diff line
		@@ -17,6 +17,7 @@ from deepchem.utils.evaluate import GeneratorEvaluator


		class TensorGraph(Model):

		def __init__(self,
		tensorboard=False,
		tensorboard_log_frequency=100,

deepchem/models/tensorgraph/tests/test_tensor_graph.py

+12 −11

Original line number	Diff line number	Diff line
		@@ -246,4 +246,5 @@ class TestTensorGraph(unittest.TestCase):
		databag.iterbatches(
		epochs=1, batch_size=tg.batch_size, pad_batches=True))
		prediction = tg.predict_proba_on_generator(databag.iterbatches())
		assert_true(np.all(np.isclose(prediction[:, 0], prediction[:, 1], atol=0.01)))
		assert_true(
		np.all(np.isclose(prediction[:, 0], prediction[:, 1], atol=0.01)))

Admin message