Fixing broken syntax from mask removal (c9fa67cd) · Commits · 钟慕尧 / deepchem

deepchem/nn/activations.py

+1 −0

Original line number	Diff line number	Diff line
		@@ -8,6 +8,7 @@ from __future__ import division
		from __future__ import unicode_literals

		import six
		import tensorflow as tf
		from deepchem.nn import model_ops
		from deepchem.nn.model_ops import get_ndim

deepchem/nn/copy.py

+6 −4

Original line number	Diff line number	Diff line
		@@ -146,6 +146,7 @@ class Node(object):
		tensor_indices = [0 for _ in range(len(inbound_layers))]

		input_tensors = []
		input_shapes = []

		for inbound_layer, node_index, tensor_index in zip(
		inbound_layers, node_indices, tensor_indices):
		@@ -157,7 +158,7 @@ class Node(object):

		if len(input_tensors) == 1:
		output_tensors = to_list(outbound_layer.call(
		input_tensors[0])
		input_tensors[0]))
		# TODO: try to auto-infer shape
		# if exception is raised by get_output_shape_for.
		output_shapes = to_list(outbound_layer.get_output_shape_for(input_shapes[0]))
		@@ -1045,14 +1046,15 @@ class Dropout(Layer):
		a fraction `p` of input units to 0 at each update during training time,
		which helps prevent overfitting.

		# Arguments
		Parameters
		----------
		p: float between 0 and 1. Fraction of the input units to drop.
		noise_shape: 1D integer tensor representing the shape of the
		binary dropout mask that will be multiplied with the input.
		For instance, if your inputs have shape
		`(batch_size, timesteps, features)` and
		(batch_size, timesteps, features) and
		you want the dropout mask to be the same for all timesteps,
		you can use `noise_shape=(batch_size, 1, features)`.
		you can use noise_shape=(batch_size, 1, features).
		seed: A Python integer to use as random seed.

		# References

deepchem/nn/model_ops.py

+33 −29

Original line number	Diff line number	Diff line
		@@ -12,6 +12,8 @@ import numpy as np
		import tensorflow as tf
		from tensorflow.python.training import moving_averages
		from collections import defaultdict
		# TODO(rbharath): What does this line do?
		py_all = all

		# TODO(rbharath): REMOVE GLOBAL VARS! BREAKS DEEPCHEM STYLE!
		# This is the default internal TF session used by Keras.
		@@ -85,28 +87,20 @@ def in_train_phase(x, alt):
		x._uses_learning_phase = True
		return x

		def _cond(condition, then_lambda, else_lambda):
		"""Backwards compatible interface to tf.cond prior to public introduction.
		"""
		try:
		cond_fn = tf.cond
		except AttributeError:
		from tensorflow.python.ops import control_flow_ops
		cond_fn = control_flow_ops.cond
		return cond_fn(condition, then_lambda, else_lambda)

		def switch(condition, then_expression, else_expression):
		"""Switches between two operations
		depending on a scalar value (`int` or `bool`).
		Note that both `then_expression` and `else_expression`
		should be symbolic tensors of the same shape.

		# Arguments
		Parameters
		----------
		condition: scalar tensor.
		then_expression: either a tensor, or a callable that returns a tensor.
		else_expression: either a tensor, or a callable that returns a tensor.

		# Returns
		Returns
		-------
		The selected tensor.
		"""
		if condition.dtype != tf.bool:
		@@ -121,17 +115,16 @@ def switch(condition, then_expression, else_expression):
		return else_expression
		else:
		else_expression_fn = else_expression
		x = _cond(condition,
		then_expression_fn,
		else_expression_fn)
		x = tf.cond(condition, then_expression_fn, else_expression_fn)
		return x

		def normalize_batch_in_training(x, gamma, beta,
		reduction_axes, epsilon=1e-3):
		"""Computes mean and std for batch then apply batch_normalization on batch.

		# Returns
		A tuple length of 3, `(normalized_tensor, mean, variance)`.
		Returns
		-------
		A tuple length of 3, (normalized_tensor, mean, variance).
		"""
		mean, var = tf.nn.moments(x, reduction_axes,
		shift=None, name=None, keep_dims=False)
		@@ -142,7 +135,7 @@ def normalize_batch_in_training(x, gamma, beta,
		else:
		# need broadcasting
		target_shape = []
		for axis in range(ndim(x)):
		for axis in range(get_ndim(x)):
		if axis in reduction_axes:
		target_shape.append(1)
		else:
		@@ -162,20 +155,13 @@ def eval(x):
		"""Evaluates the value of a variable.
		Returns a Numpy array.

		# Arguments
		Parameters
		----------
		x: A variable.

		# Returns
		Returns
		-------
		A Numpy array.

		# Examples
		```python
		>>> from keras import backend as K
		>>> kvar = K.variable(np.array([[1, 2], [3, 4]]), dtype='float32')
		>>> K.eval(kvar)
		array([[ 1., 2.],
		[ 3., 4.]], dtype=float32)
		```
		"""
		return to_dense(x).eval(session=get_session())

		@@ -372,6 +358,24 @@ def batch_set_value(tuples):
		feed_dict[assign_placeholder] = value
		get_session().run(assign_ops, feed_dict=feed_dict)

		def _initialize_variables():
		if hasattr(tf, 'global_variables'):
		variables = tf.global_variables()
		else:
		variables = tf.all_variables()

		uninitialized_variables = []
		for v in variables:
		if not hasattr(v, '_keras_initialized') or not v._keras_initialized:
		uninitialized_variables.append(v)
		v._keras_initialized = True
		if uninitialized_variables:
		sess = get_session()
		if hasattr(tf, 'variables_initializer'):
		sess.run(tf.variables_initializer(uninitialized_variables))
		else:
		sess.run(tf.initialize_variables(uninitialized_variables))

		# TODO(rbharath): DANGEROUS! THIS IS LEAKY AND BREAKS DEEPCHEM STYLE!
		def get_session():
		"""Returns the TF session to be used by the backend.

Admin message