Coverage for /pythoncovmergedfiles/medio/medio/usr/local/lib/python3.8/site-packages/tensorflow/python/ops/tensor_array_grad.py: 42%
100 statements
« prev ^ index » next coverage.py v7.4.0, created at 2024-01-03 07:57 +0000
1# Copyright 2015 The TensorFlow Authors. 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"""Gradients for operators defined in tensor_array_ops.py."""
16from tensorflow.python.framework import ops
17from tensorflow.python.ops import array_ops
18from tensorflow.python.ops import tensor_array_ops
20# TODO(b/31222613): These ops may be differentiable, and there may be
21# latent bugs here.
22ops.NotDifferentiable("TensorArray")
23ops.NotDifferentiable("TensorArrayGrad")
24ops.NotDifferentiable("TensorArraySize")
25ops.NotDifferentiable("TensorArrayClose")
27ops.NotDifferentiable("TensorArrayV2")
28ops.NotDifferentiable("TensorArrayGradV2")
29ops.NotDifferentiable("TensorArraySizeV2")
30ops.NotDifferentiable("TensorArrayCloseV2")
32ops.NotDifferentiable("TensorArrayV3")
33ops.NotDifferentiable("TensorArrayGradV3")
34ops.NotDifferentiable("TensorArrayGradWithShape")
35ops.NotDifferentiable("TensorArraySizeV3")
36ops.NotDifferentiable("TensorArrayCloseV3")
39def _GetGradSource(op_or_tensor):
40 """Identify which call to tf.gradients created this gradient op or tensor.
42 TensorArray gradient calls use an accumulator TensorArray object. If
43 multiple gradients are calculated and run in the same session, the multiple
44 gradient nodes may accidentally flow through the same accumulator TensorArray.
45 This double counting breaks the TensorArray gradient flow.
47 The solution is to identify which gradient call this particular
48 TensorArray*Grad is being called in, by looking at the input gradient
49 tensor's name, and create or lookup an accumulator gradient TensorArray
50 associated with this specific call. This solves any confusion and ensures
51 different gradients from the same forward graph get their own accumulators.
53 This function creates the unique label associated with the tf.gradients call
54 that is used to create the gradient TensorArray.
56 Args:
57 op_or_tensor: `Tensor` or `Operation` which is an input to a
58 TensorArray*Grad call.
60 Returns:
61 A python string, the unique label associated with this particular
62 gradients calculation.
64 Raises:
65 ValueError: If not called within a gradients calculation.
66 """
67 name_tokens = op_or_tensor.name.split("/")
68 grad_pos = [i for i, x in enumerate(name_tokens) if x.startswith("gradients")]
69 if not grad_pos:
70 raise ValueError(
71 "Expected op/tensor name to start with gradients (excluding scope)"
72 f", got: {op_or_tensor.name}. This means that a tf.gradients op with "
73 "this op in its dependency path has a custom name that does not start "
74 "with 'gradients'. Please make sure all calls to tf.gradients that "
75 "have non-empty `name` arguments use names that start with "
76 "'gradients'.")
77 return "/".join(name_tokens[:grad_pos[-1] + 1])
80@ops.RegisterGradient("TensorArrayRead")
81@ops.RegisterGradient("TensorArrayReadV2")
82@ops.RegisterGradient("TensorArrayReadV3")
83def _TensorArrayReadGrad(op, grad):
84 """Gradient for TensorArrayRead.
86 Args:
87 op: Forward TensorArrayRead op.
88 grad: Gradient `Tensor` to TensorArrayRead.
90 Returns:
91 A flow `Tensor`, which can be used in control dependencies to
92 force the write of `grad` to the gradient `TensorArray`.
93 """
94 # Note: the forward flow dependency in the call to grad() is necessary for
95 # the case of dynamic sized TensorArrays. When creating the gradient
96 # TensorArray, the final size of the forward array must be known.
97 # For this we need to wait until it has been created by depending on
98 # the input flow of the original op.
99 handle = op.inputs[0]
100 index = op.inputs[1]
101 flow = op.inputs[2]
102 dtype = op.get_attr("dtype")
103 grad_source = _GetGradSource(grad)
104 g = (tensor_array_ops.TensorArray(dtype=dtype, handle=handle, flow=flow,
105 colocate_with_first_write_call=False)
106 .grad(source=grad_source, flow=flow))
107 w_g = g.write(index, grad)
108 return [None, None, w_g.flow]
111@ops.RegisterGradient("TensorArrayWrite")
112@ops.RegisterGradient("TensorArrayWriteV2")
113@ops.RegisterGradient("TensorArrayWriteV3")
114def _TensorArrayWriteGrad(op, flow):
115 """Gradient for TensorArrayWrite.
117 Args:
118 op: Forward TensorArrayWrite op.
119 flow: Gradient `Tensor` flow to TensorArrayWrite.
121 Returns:
122 A grad `Tensor`, the gradient created in an upstream ReadGrad or PackGrad.
123 """
124 # handle is the output store_handle of TensorArrayReadGrad or
125 # the handle output of TensorArrayWriteGrad. we must use this one.
126 handle = op.inputs[0]
127 index = op.inputs[1]
128 dtype = op.get_attr("T")
129 grad_source = _GetGradSource(flow)
130 flow_out = array_ops.identity(op.outputs[0], "flow_out")
131 # Avoid a race condition where the TensorArrayGrad op is executed before the
132 # final TensorArrayWrite by adding a control dependency on the output flow of
133 # the write to the input flow to the TensorArrayGrad.
134 with ops.control_dependencies([flow_out]):
135 flow = array_ops.identity(flow, "write_barrier")
136 g = (tensor_array_ops.TensorArray(dtype=dtype, handle=handle, flow=flow,
137 colocate_with_first_write_call=False)
138 .grad(source=grad_source, flow=flow))
139 grad = g.read(index)
140 return [None, None, grad, flow]
143@ops.RegisterGradient("TensorArrayGather")
144@ops.RegisterGradient("TensorArrayGatherV2")
145@ops.RegisterGradient("TensorArrayGatherV3")
146def _TensorArrayGatherGrad(op, grad):
147 """Gradient for TensorArrayGather.
149 Args:
150 op: Forward TensorArrayGather op.
151 grad: Gradient `Tensor` to TensorArrayGather.
153 Returns:
154 A flow `Tensor`, which can be used in control dependencies to
155 force the write of `grad` to the gradient `TensorArray`.
156 """
157 # Note: the forward flow dependency in the call to grad() is necessary for
158 # the case of dynamic sized TensorArrays. When creating the gradient
159 # TensorArray, the final size of the forward array must be known.
160 # For this we need to wait until it has been created by depending on
161 # the input flow of the original op.
162 handle = op.inputs[0]
163 indices = op.inputs[1]
164 flow = op.inputs[2]
165 dtype = op.get_attr("dtype")
166 grad_source = _GetGradSource(grad)
167 g = (tensor_array_ops.TensorArray(dtype=dtype, handle=handle, flow=flow,
168 colocate_with_first_write_call=False)
169 .grad(source=grad_source, flow=flow))
170 u_g = g.scatter(indices, grad)
171 return [None, None, u_g.flow]
174@ops.RegisterGradient("TensorArrayScatter")
175@ops.RegisterGradient("TensorArrayScatterV2")
176@ops.RegisterGradient("TensorArrayScatterV3")
177def _TensorArrayScatterGrad(op, flow):
178 """Gradient for TensorArrayScatter.
180 Args:
181 op: Forward TensorArrayScatter op.
182 flow: Gradient `Tensor` flow to TensorArrayScatter.
184 Returns:
185 A grad `Tensor`, the gradient created in upstream ReadGrads or PackGrad.
186 """
187 handle = op.inputs[0]
188 indices = op.inputs[1]
189 dtype = op.get_attr("T")
190 grad_source = _GetGradSource(flow)
191 flow_out = array_ops.identity(op.outputs[0], "flow_out")
192 # Avoid a race condition where the TensorArrayGrad op is executed before the
193 # TensorArrayScatter by adding a control dependency on the output flow of
194 # the scatter to the input flow to the TensorArrayGrad.
195 with ops.control_dependencies([flow_out]):
196 flow = array_ops.identity(flow, "write_barrier")
197 g = (tensor_array_ops.TensorArray(dtype=dtype, handle=handle, flow=flow,
198 colocate_with_first_write_call=False)
199 .grad(source=grad_source, flow=flow))
200 grad = g.gather(indices)
201 return [None, None, grad, flow]
204@ops.RegisterGradient("TensorArrayConcat")
205@ops.RegisterGradient("TensorArrayConcatV2")
206@ops.RegisterGradient("TensorArrayConcatV3")
207def _TensorArrayConcatGrad(op, grad, unused_lengths_grad):
208 """Gradient for TensorArrayConcat.
210 Args:
211 op: Forward TensorArrayConcat op.
212 grad: Gradient `Tensor` to TensorArrayConcat.
214 Returns:
215 A flow `Tensor`, which can be used in control dependencies to
216 force the write of `grad` to the gradient `TensorArray`.
217 """
218 # Note: the forward flow dependency in the call to grad() is necessary for
219 # the case of dynamic sized TensorArrays. When creating the gradient
220 # TensorArray, the final size of the forward array must be known.
221 # For this we need to wait until it has been created by depending on
222 # the input flow of the original op.
223 handle = op.inputs[0]
224 flow = op.inputs[1]
225 lengths = op.outputs[1]
226 dtype = op.get_attr("dtype")
227 grad_source = _GetGradSource(grad)
228 g = (tensor_array_ops.TensorArray(dtype=dtype, handle=handle, flow=flow,
229 colocate_with_first_write_call=False)
230 .grad(source=grad_source, flow=flow))
231 u_g = g.split(grad, lengths=lengths)
232 # handle, flow_in
233 return [None, u_g.flow]
236@ops.RegisterGradient("TensorArraySplit")
237@ops.RegisterGradient("TensorArraySplitV2")
238@ops.RegisterGradient("TensorArraySplitV3")
239def _TensorArraySplitGrad(op, flow):
240 """Gradient for TensorArraySplit.
242 Args:
243 op: Forward TensorArraySplit op.
244 flow: Gradient `Tensor` flow to TensorArraySplit.
246 Returns:
247 A grad `Tensor`, the gradient created in upstream ReadGrads or PackGrad.
248 """
249 handle = op.inputs[0]
250 dtype = op.get_attr("T")
251 grad_source = _GetGradSource(flow)
252 flow_out = array_ops.identity(op.outputs[0], "flow_out")
253 # Avoid a race condition where the TensorArrayGrad op is executed before the
254 # TensorArraySplit by adding a control dependency on the output flow of
255 # the split to the input flow to the TensorArrayGrad.
256 with ops.control_dependencies([flow_out]):
257 flow = array_ops.identity(flow, "write_barrier")
258 g = (tensor_array_ops.TensorArray(dtype=dtype, handle=handle, flow=flow,
259 colocate_with_first_write_call=False)
260 .grad(source=grad_source, flow=flow))
261 grad = g.concat()
262 # handle, value, lengths, flow_in
263 return [None, grad, None, flow]