/external/tensorflow/tensorflow/python/keras/layers/ |
D | gru_v2_test.py | 77 layer = rnn.GRU(1, 88 layer = rnn.GRU(1, activation=nn.tanh) 91 layer = rnn.GRU(1, recurrent_activation=nn.sigmoid) 109 layer = rnn.GRU(rnn_state_size) 126 layer = rnn.GRU(units, input_shape=(None, embedding_dim)) 139 model.add(rnn.GRU(10, return_sequences=True, unroll=False)) 140 model.add(rnn.GRU(5, return_sequences=True, unroll=False)) 147 layer_class = rnn.GRU 179 gru_layer = rnn_v1.GRU(rnn_state_size, 191 cudnn_layer = rnn.GRU(rnn_state_size, [all …]
|
D | gru_test.py | 45 keras.layers.GRU, 59 keras.layers.GRU, 71 layer = keras.layers.GRU(units, input_shape=(None, embedding_dim)) 88 keras.layers.GRU, 95 layer = keras.layers.GRU(2, recurrent_dropout=0.1, implementation=2) 106 keras.layers.GRU, 125 gru_layer = keras.layers.GRU(units, 139 layer_class = keras.layers.GRU 159 layer_class = keras.layers.GRU 233 layer_class = keras.layers.GRU [all …]
|
D | recurrent_v2_test.py | 41 @parameterized.parameters([rnn_v2.LSTM, rnn_v2.GRU]) 68 @parameterized.parameters([rnn_v2.LSTM, rnn_v2.GRU]) 95 @parameterized.parameters([rnn_v2.LSTM, rnn_v2.GRU]) 109 x = keras.layers.GRU(64, activation='relu', name='GRU', dropout=0.1)(inputs) 117 @parameterized.parameters([rnn_v2.LSTM, rnn_v2.GRU])
|
D | serialization_test.py | 154 @parameterized.parameters([rnn_v1.GRU, rnn_v2.GRU]) 163 self.assertIsInstance(new_layer, rnn_v2.GRU) 165 self.assertIsInstance(new_layer, rnn_v1.GRU) 166 self.assertNotIsInstance(new_layer, rnn_v2.GRU)
|
D | __init__.py | 224 from tensorflow.python.keras.layers.recurrent_v2 import GRU 228 from tensorflow.python.keras.layers.recurrent import GRU as GRUV1 232 GRUV2 = GRU 237 from tensorflow.python.keras.layers.recurrent import GRU 241 from tensorflow.python.keras.layers.recurrent_v2 import GRU as GRUV2 245 GRUV1 = GRU
|
D | recurrent_test.py | 641 [keras.layers.SimpleRNN, keras.layers.GRU, keras.layers.LSTM]) 756 layer=[rnn_v1.SimpleRNN, rnn_v1.GRU, rnn_v1.LSTM, 757 rnn_v2.GRU, rnn_v2.LSTM], 1473 rnn_output = keras.layers.GRU( 1585 rnn_v1.SimpleRNN, rnn_v1.GRU, rnn_v1.LSTM, rnn_v2.GRU, rnn_v2.LSTM 1716 [rnn_v1.SimpleRNN, rnn_v1.GRU, rnn_v1.LSTM, rnn_v2.GRU, rnn_v2.LSTM])
|
D | cudnn_recurrent_test.py | 298 rnn_layer_class = keras.layers.GRU 380 rnn_layer_class = keras.layers.GRU
|
D | recurrent_v2.py | 221 class GRU(recurrent.DropoutRNNCellMixin, recurrent.GRU): class 378 super(GRU, self).__init__(
|
/external/tensorflow/tensorflow/core/api_def/base_api/ |
D | api_def_GRUBlockCell.pbtxt | 4 summary: "Computes the GRU cell forward propagation for 1 time step." 7 x: Input to the GRU cell. 8 h_prev: State input from the previous GRU cell. 18 h: Current state of the GRU cell.
|
D | api_def_GRUBlockCellGrad.pbtxt | 4 summary: "Computes the GRU cell back-propagation for 1 time step." 7 x: Input to the GRU cell. 8 h_prev: State input from the previous GRU cell.
|
/external/rnnoise/training/ |
D | rnn_train.py | 11 from keras.layers import GRU 65 vad_gru = GRU(24, activation='tanh', recurrent_activation='sigmoid', return_sequences=True, name='v… 68 noise_gru = GRU(48, activation='relu', recurrent_activation='sigmoid', return_sequences=True, name=… 71 denoise_gru = GRU(96, activation='tanh', recurrent_activation='sigmoid', return_sequences=True, nam…
|
D | dump_rnn.py | 8 from keras.layers import GRU
|
/external/rnnoise/src/ |
D | rnn_train.py | 10 from keras.layers import GRU 24 x = GRU(128, activation='tanh', recurrent_activation='sigmoid', return_sequences=True)(x)
|
/external/libopus/scripts/ |
D | rnn_train.py | 10 from keras.layers import GRU 30 x = GRU(12, dropout=0.1, recurrent_dropout=0.1, activation='tanh', recurrent_activation='sigmoid', …
|
D | dump_rnn.py | 8 from keras.layers import GRU
|
/external/libopus/training/ |
D | rnn_dump.py | 10 from keras.layers import GRU 42 x = GRU(24, activation='tanh', recurrent_activation='sigmoid', return_sequences=True)(x)
|
D | rnn_train.py | 10 from keras.layers import GRU 61 x = GRU(24, recurrent_activation='sigmoid', activation='tanh', return_sequences=True, kernel_constr…
|
/external/tensorflow/tensorflow/security/advisory/ |
D | tfsa-2020-033.md | 7 Running an LSTM/GRU model where the LSTM/GRU layer receives an input with
|
/external/tensorflow/tensorflow/python/keras/distribute/ |
D | keras_rnn_model_correctness_test.py | 82 return rnn_v2.GRU 84 return rnn_v1.GRU
|
/external/tensorflow/tensorflow/tools/api/golden/v2/ |
D | tensorflow.keras.layers.-g-r-u.pbtxt | 1 path: "tensorflow.keras.layers.GRU" 3 is_instance: "<class \'tensorflow.python.keras.layers.recurrent_v2.GRU\'>" 5 is_instance: "<class \'tensorflow.python.keras.layers.recurrent.GRU\'>"
|
D | tensorflow.keras.layers.pbtxt | 168 name: "GRU"
|
/external/tensorflow/tensorflow/python/keras/mixed_precision/ |
D | layer_correctness_test.py | 135 ('GRU', lambda: recurrent.GRU(units=4), (4, 4, 4)), 137 ('GRUV2', lambda: recurrent_v2.GRU(units=4), (4, 4, 4)),
|
/external/tensorflow/tensorflow/python/keras/benchmarks/layer_benchmarks/ |
D | layer_benchmarks_test.py | 121 ("GRU_small_shape", tf.keras.layers.GRU, 284 tf.keras.layers.ConvLSTM2D, tf.keras.layers.GRU, tf.keras.layers.RNN,
|
/external/tensorflow/tensorflow/tools/api/golden/v1/ |
D | tensorflow.keras.layers.-g-r-u.pbtxt | 1 path: "tensorflow.keras.layers.GRU" 3 is_instance: "<class \'tensorflow.python.keras.layers.recurrent.GRU\'>"
|
/external/tensorflow/tensorflow/python/ops/numpy_ops/g3doc/ |
D | TensorFlow_NumPy_Text_Generation.ipynb | 428 …nd some low-level TF ops. A `Model` object has three layers: `Embedding`, `GRU` and `Dense`. `Embe… 437 …"Our model (more precisely the `GRU` layer) is stateful, because each call of `__call__` will chan… 486 " \"\"\"Builds a traditional GRU cell with dense internal transformations.\n", 512 " # The dense layer input is the input and half of the GRU state.\n", 528 "class GRU:\n", 607 " self._gru = GRU(rnn_units, forget_bias=forget_bias, stateful=stateful)\n", 654 …"For each character the model looks up the embedding, runs the GRU one timestep with the embedding…
|