| /external/tensorflow/tensorflow/python/keras/layers/ |
| D | __init__.py | 216 from tensorflow.python.keras.layers.recurrent import RNN
217 from tensorflow.python.keras.layers.recurrent import AbstractRNNCell
218 from tensorflow.python.keras.layers.recurrent import StackedRNNCells
219 from tensorflow.python.keras.layers.recurrent import SimpleRNNCell
220 from tensorflow.python.keras.layers.recurrent import PeepholeLSTMCell
221 from tensorflow.python.keras.layers.recurrent import SimpleRNN
228 from tensorflow.python.keras.layers.recurrent import GRU as GRUV1
229 from tensorflow.python.keras.layers.recurrent import GRUCell as GRUCellV1
230 from tensorflow.python.keras.layers.recurrent import LSTM as LSTMV1
231 from tensorflow.python.keras.layers.recurrent import LSTMCell as LSTMCellV1
[all …]
|
| D | rnn_cell_wrapper_v2.py | 28 from tensorflow.python.keras.layers import recurrent
34 class _RNNCellWrapperV2(recurrent.AbstractRNNCell):
104 if isinstance(self.cell, recurrent.LSTMCell):
|
| D | BUILD | 52 ":recurrent",
109 ":recurrent",
168 ":recurrent",
380 name = "recurrent",
381 srcs = ["recurrent.py"],
415 ":recurrent",
442 ":recurrent",
453 ":recurrent",
|
| D | recurrent_v2.py | 34 from tensorflow.python.keras.layers import recurrent
109 class GRUCell(recurrent.GRUCell):
221 class GRU(recurrent.DropoutRNNCellMixin, recurrent.GRU):
843 class LSTMCell(recurrent.LSTMCell):
959 class LSTM(recurrent.DropoutRNNCellMixin, recurrent.LSTM):
|
| D | serialization.py | 45 from tensorflow.python.keras.layers import recurrent
72 preprocessing_text_vectorization_v1, recurrent, wrappers,
|
| /external/deqp-deps/SPIRV-Tools/source/opt/ |
| D | scalar_analysis.cpp | 438 SERecurrentNode* recurrent = node->AsSERecurrentNode(); in BuildGraphWithoutRecurrentTerm() local
439 if (recurrent) { in BuildGraphWithoutRecurrentTerm()
440 if (recurrent->GetLoop() == loop) { in BuildGraphWithoutRecurrentTerm()
441 return recurrent->GetOffset(); in BuildGraphWithoutRecurrentTerm()
450 recurrent = itr->AsSERecurrentNode(); in BuildGraphWithoutRecurrentTerm()
451 if (recurrent && recurrent->GetLoop() == loop) { in BuildGraphWithoutRecurrentTerm()
452 new_children.push_back(recurrent->GetOffset()); in BuildGraphWithoutRecurrentTerm()
597 const SERecurrentNode* recurrent = node->AsSERecurrentNode(); in operator ()() local
601 if (recurrent) { in operator ()()
602 PushToString(reinterpret_cast<uintptr_t>(recurrent->GetLoop()), in operator ()()
[all …]
|
| D | scalar_analysis_simplification.cpp | 105 SERecurrentNode* UpdateCoefficient(SERecurrentNode* recurrent,
288 SERecurrentNode* recurrent, int64_t coefficient_update) const { in UpdateCoefficient() argument
290 recurrent->GetParentAnalysis(), recurrent->GetLoop())}; in UpdateCoefficient()
293 recurrent->GetCoefficient(), in UpdateCoefficient()
303 analysis_.CreateNegation(recurrent->GetOffset())); in UpdateCoefficient()
305 new_recurrent_node->AddOffset(recurrent->GetOffset()); in UpdateCoefficient()
|
| /external/swiftshader/third_party/SPIRV-Tools/source/opt/ |
| D | scalar_analysis.cpp | 438 SERecurrentNode* recurrent = node->AsSERecurrentNode(); in BuildGraphWithoutRecurrentTerm() local
439 if (recurrent) { in BuildGraphWithoutRecurrentTerm()
440 if (recurrent->GetLoop() == loop) { in BuildGraphWithoutRecurrentTerm()
441 return recurrent->GetOffset(); in BuildGraphWithoutRecurrentTerm()
450 recurrent = itr->AsSERecurrentNode(); in BuildGraphWithoutRecurrentTerm()
451 if (recurrent && recurrent->GetLoop() == loop) { in BuildGraphWithoutRecurrentTerm()
452 new_children.push_back(recurrent->GetOffset()); in BuildGraphWithoutRecurrentTerm()
597 const SERecurrentNode* recurrent = node->AsSERecurrentNode(); in operator ()() local
601 if (recurrent) { in operator ()()
602 PushToString(reinterpret_cast<uintptr_t>(recurrent->GetLoop()), in operator ()()
[all …]
|
| D | scalar_analysis_simplification.cpp | 105 SERecurrentNode* UpdateCoefficient(SERecurrentNode* recurrent,
288 SERecurrentNode* recurrent, int64_t coefficient_update) const { in UpdateCoefficient() argument
290 recurrent->GetParentAnalysis(), recurrent->GetLoop())}; in UpdateCoefficient()
293 recurrent->GetCoefficient(), in UpdateCoefficient()
303 analysis_.CreateNegation(recurrent->GetOffset())); in UpdateCoefficient()
305 new_recurrent_node->AddOffset(recurrent->GetOffset()); in UpdateCoefficient()
|
| /external/angle/third_party/vulkan-deps/spirv-tools/src/source/opt/ |
| D | scalar_analysis.cpp | 438 SERecurrentNode* recurrent = node->AsSERecurrentNode(); in BuildGraphWithoutRecurrentTerm() local
439 if (recurrent) { in BuildGraphWithoutRecurrentTerm()
440 if (recurrent->GetLoop() == loop) { in BuildGraphWithoutRecurrentTerm()
441 return recurrent->GetOffset(); in BuildGraphWithoutRecurrentTerm()
450 recurrent = itr->AsSERecurrentNode(); in BuildGraphWithoutRecurrentTerm()
451 if (recurrent && recurrent->GetLoop() == loop) { in BuildGraphWithoutRecurrentTerm()
452 new_children.push_back(recurrent->GetOffset()); in BuildGraphWithoutRecurrentTerm()
597 const SERecurrentNode* recurrent = node->AsSERecurrentNode(); in operator ()() local
601 if (recurrent) { in operator ()()
602 PushToString(reinterpret_cast<uintptr_t>(recurrent->GetLoop()), in operator ()()
[all …]
|
| D | scalar_analysis_simplification.cpp | 105 SERecurrentNode* UpdateCoefficient(SERecurrentNode* recurrent,
288 SERecurrentNode* recurrent, int64_t coefficient_update) const { in UpdateCoefficient() argument
290 recurrent->GetParentAnalysis(), recurrent->GetLoop())}; in UpdateCoefficient()
293 recurrent->GetCoefficient(), in UpdateCoefficient()
303 analysis_.CreateNegation(recurrent->GetOffset())); in UpdateCoefficient()
305 new_recurrent_node->AddOffset(recurrent->GetOffset()); in UpdateCoefficient()
|
| /external/tensorflow/tensorflow/python/keras/mixed_precision/ |
| D | layer_correctness_test.py | 42 from tensorflow.python.keras.layers import recurrent
133 ('SimpleRNN', lambda: recurrent.SimpleRNN(units=4),
135 ('GRU', lambda: recurrent.GRU(units=4), (4, 4, 4)),
136 ('LSTM', lambda: recurrent.LSTM(units=4), (4, 4, 4)),
142 lambda: wrappers.Bidirectional(recurrent.SimpleRNN(units=4)), (2, 2, 2)),
|
| /external/tensorflow/tensorflow/python/keras/feature_column/ |
| D | sequence_feature_column_integration_test.py | 35 from tensorflow.python.keras.layers import recurrent
106 rnn_layer = recurrent.RNN(recurrent.SimpleRNNCell(10))
|
| /external/tensorflow/tensorflow/python/keras/saving/saved_model/ |
| D | serialized_attributes.py | 39 recurrent = LazyLoader( variable
149 elif isinstance(obj, recurrent.RNN):
|
| /external/tensorflow/tensorflow/tools/api/golden/v1/ |
| D | tensorflow.keras.experimental.-peephole-l-s-t-m-cell.pbtxt | 3 is_instance: "<class \'tensorflow.python.keras.layers.recurrent.PeepholeLSTMCell\'>"
4 is_instance: "<class \'tensorflow.python.keras.layers.recurrent.LSTMCell\'>"
5 is_instance: "<class \'tensorflow.python.keras.layers.recurrent.DropoutRNNCellMixin\'>"
|
| D | tensorflow.keras.layers.-simple-r-n-n-cell.pbtxt | 3 is_instance: "<class \'tensorflow.python.keras.layers.recurrent.SimpleRNNCell\'>"
4 is_instance: "<class \'tensorflow.python.keras.layers.recurrent.DropoutRNNCellMixin\'>"
|
| D | tensorflow.keras.layers.-l-s-t-m-cell.pbtxt | 3 is_instance: "<class \'tensorflow.python.keras.layers.recurrent.LSTMCell\'>"
4 is_instance: "<class \'tensorflow.python.keras.layers.recurrent.DropoutRNNCellMixin\'>"
|
| D | tensorflow.keras.layers.-g-r-u-cell.pbtxt | 3 is_instance: "<class \'tensorflow.python.keras.layers.recurrent.GRUCell\'>"
4 is_instance: "<class \'tensorflow.python.keras.layers.recurrent.DropoutRNNCellMixin\'>"
|
| /external/tensorflow/tensorflow/tools/api/golden/v2/ |
| D | tensorflow.keras.experimental.-peephole-l-s-t-m-cell.pbtxt | 3 is_instance: "<class \'tensorflow.python.keras.layers.recurrent.PeepholeLSTMCell\'>"
4 is_instance: "<class \'tensorflow.python.keras.layers.recurrent.LSTMCell\'>"
5 is_instance: "<class \'tensorflow.python.keras.layers.recurrent.DropoutRNNCellMixin\'>"
|
| D | tensorflow.keras.layers.-g-r-u.pbtxt | 4 is_instance: "<class \'tensorflow.python.keras.layers.recurrent.DropoutRNNCellMixin\'>"
5 is_instance: "<class \'tensorflow.python.keras.layers.recurrent.GRU\'>"
6 is_instance: "<class \'tensorflow.python.keras.layers.recurrent.RNN\'>"
|
| D | tensorflow.keras.layers.-l-s-t-m.pbtxt | 4 is_instance: "<class \'tensorflow.python.keras.layers.recurrent.DropoutRNNCellMixin\'>"
5 is_instance: "<class \'tensorflow.python.keras.layers.recurrent.LSTM\'>"
6 is_instance: "<class \'tensorflow.python.keras.layers.recurrent.RNN\'>"
|
| D | tensorflow.keras.layers.-l-s-t-m-cell.pbtxt | 4 is_instance: "<class \'tensorflow.python.keras.layers.recurrent.LSTMCell\'>"
5 is_instance: "<class \'tensorflow.python.keras.layers.recurrent.DropoutRNNCellMixin\'>"
|
| D | tensorflow.keras.layers.-g-r-u-cell.pbtxt | 4 is_instance: "<class \'tensorflow.python.keras.layers.recurrent.GRUCell\'>"
5 is_instance: "<class \'tensorflow.python.keras.layers.recurrent.DropoutRNNCellMixin\'>"
|
| /external/rnnoise/ |
| D | README | 1 RNNoise is a noise suppression library based on a recurrent neural network.
|
| /external/tensorflow/tensorflow/lite/g3doc/convert/ |
| D | rnn.md | 82 1. The dimension 0 of the **recurrent\_weight** tensor is the number of
84 1. The **weight** and **recurrent\_kernel** tensors are transposed.
85 1. The transposed weight, transposed recurrent\_kernel and **bias** tensors are
172 1. The **{input, recurrent}** to **{cell, input gate, forget gate, output
|