data_flow_grad.py revision e14090d217fc4e7e49ac04ccbc50acdba8b9f120 
1# Copyright 2015 Google Inc. All Rights Reserved.
2#
3# Licensed under the Apache License, Version 2.0 (the "License");
4# you may not use this file except in compliance with the License.
5# You may obtain a copy of the License at
6#
7#     http://www.apache.org/licenses/LICENSE-2.0
8#
9# Unless required by applicable law or agreed to in writing, software
10# distributed under the License is distributed on an "AS IS" BASIS,
11# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12# See the License for the specific language governing permissions and
13# limitations under the License.
14# ==============================================================================
15
16"""Gradients for operators defined in data_flow_ops.py."""
17from __future__ import absolute_import
18from __future__ import division
19from __future__ import print_function
20
21from six.moves import xrange  # pylint: disable=redefined-builtin
22from tensorflow.python.framework import dtypes
23from tensorflow.python.framework import ops
24from tensorflow.python.ops import array_ops
25from tensorflow.python.ops import constant_op
26from tensorflow.python.ops import data_flow_ops
27from tensorflow.python.ops import math_ops
28
29
30@ops.RegisterGradient("DynamicPartition")
31def _DynamicPartitionGrads(op, *grads):
32  """Gradients for DynamicPartition."""
33  data = op.inputs[0]
34  indices = op.inputs[1]
35  num_partitions = op.get_attr("num_partitions")
36
37  prefix_shape = array_ops.shape(indices)
38  original_indices = array_ops.reshape(
39      math_ops.range(math_ops.reduce_prod(prefix_shape)), prefix_shape)
40  partitioned_indices = data_flow_ops.dynamic_partition(
41      original_indices, indices, num_partitions)
42  reconstructed = data_flow_ops.dynamic_stitch(partitioned_indices, grads)
43  reconstructed = array_ops.reshape(reconstructed, array_ops.shape(data))
44  return [reconstructed, None]
45
46
47@ops.RegisterGradient("DynamicStitch")
48def _DynamicStitchGrads(op, grad):
49  """Gradients for DynamicStitch."""
50
51  num_values = len(op.inputs) // 2
52  indices_grad = [None] * num_values
53
54  def AsInt32(x):
55    return (x if op.inputs[0].dtype == dtypes.int32 else
56            math_ops.cast(x, dtypes.int32))
57  inputs = [AsInt32(op.inputs[i]) for i in xrange(num_values)]
58  if isinstance(grad, ops.IndexedSlices):
59    output_shape = array_ops.shape(op.outputs[0])
60    output_rows = output_shape[0]
61    grad = math_ops.unsorted_segment_sum(grad.values, grad.indices, output_rows)
62  values_grad = [array_ops.gather(grad, inp) for inp in inputs]
63  return indices_grad + values_grad
64
65
66ops.NoGradient("Queue")
67ops.NoGradient("QueueEnqueue")
68ops.NoGradient("QueueEnqueueMany")
69ops.NoGradient("QueueDequeue")
70ops.NoGradient("QueueDequeueMany")
71ops.NoGradient("QueueClose")
72ops.NoGradient("QueueSize")
73
74ops.NoGradient("Stack")
75ops.NoGradient("StackPush")
76ops.NoGradient("StackPop")
77ops.NoGradient("StackClose")
78
79ops.NoGradient("TensorArray")
80ops.NoGradient("TensorArrayGrad")
81ops.NoGradient("TensorArrayClose")
82
83
84@ops.RegisterGradient("TensorArrayRead")
85def _TensorArrayReadGrad(op, grad):
86  handle = op.inputs[0]
87  index = op.inputs[1]
88  dtype = op.get_attr("dtype")
89  g = data_flow_ops.TensorArray(size=None, dtype=dtype, handle=handle).grad()
90  w_g = g.write(index, grad)
91  return [None, None, w_g.flow]
92
93
94@ops.RegisterGradient("TensorArrayWrite")
95def _TensorArrayWriteGrad(op, flow):
96  # handle is the output store_handle of TensorArrayReadGrad or
97  # the handle output of TensorArrayWriteGrad.  we must use this one.
98  handle = op.inputs[0]
99  index = op.inputs[1]
100  dtype = op.get_attr("T")
101  g = data_flow_ops.TensorArray(size=None, dtype=dtype, handle=handle).grad()
102  with ops.control_dependencies([flow]):
103    grad = g.read(index)
104  return [None, None, grad, flow]
105
106
107@ops.RegisterGradient("TensorArrayPack")
108def _TensorArrayPackGrad(op, grad):
109  handle = op.inputs[0]
110  dtype = op.get_attr("dtype")
111  g = data_flow_ops.TensorArray(size=None, dtype=dtype, handle=handle).grad()
112  u_g = g.unpack(grad)
113  return [None, u_g.flow]
114
115
116@ops.RegisterGradient("TensorArrayUnpack")
117def _TensorArrayUnpackGrad(op, flow):
118  # handle is the output store_handle of TensorArrayReadGrad or
119  # the handle output of TensorArrayUnpackGrad.  we must use this one.
120  handle = op.inputs[0]
121  dtype = op.get_attr("T")
122  g = data_flow_ops.TensorArray(size=None, dtype=dtype, handle=handle).grad()
123  with ops.control_dependencies([flow]):
124    grad = g.pack()
125  return [None, grad, flow]
126# pylint: enable=protected-access
127