/external/tensorflow/tensorflow/python/keras/layers/ |
serialization_test.py | 72 @parameterized.parameters([rnn_v1.LSTM, rnn_v2.LSTM]) 74 lstm = layer(5, return_sequences=True) 75 config = keras.layers.serialize(lstm) 76 self.assertEqual(config['class_name'], 'LSTM') 81 self.assertIsInstance(new_layer, rnn_v2.LSTM) 83 self.assertIsInstance(new_layer, rnn_v1.LSTM) 84 self.assertNotIsInstance(new_layer, rnn_v2.LSTM)
|
lstm_v2_test.py | 71 layer = rnn.LSTM( 90 layer = rnn.LSTM(units, return_sequences=True) 100 layer = rnn.LSTM(units, input_shape=(None, embedding_dim)) 113 model.add(rnn.LSTM(10, return_sequences=True, unroll=False)) 114 model.add(rnn.LSTM(5, return_sequences=True, unroll=False)) 121 layer_class = rnn.LSTM 137 layer = rnn.LSTM(units) 169 layer = rnn.LSTM(units) 188 layer = rnn.LSTM(units, stateful=True) 228 output = rnn.LSTM(units) [all...] |
lstm_test.py | 15 """Tests for LSTM layer.""" 42 keras.layers.LSTM, 57 layer = keras.layers.LSTM(units, return_sequences=True) 67 layer = keras.layers.LSTM(units, input_shape=(None, embedding_dim)) 83 keras.layers.LSTM, 96 keras.layers.LSTM, 103 layer_class = keras.layers.LSTM 121 layer_class = keras.layers.LSTM 149 layer_class = keras.layers.LSTM 165 layer = keras.layers.LSTM(units [all...] |
recurrent_v2_test.py | 15 """Tests for recurrent v2 layers functionality other than GRU, LSTM. 39 @parameterized.parameters([rnn_v2.LSTM, rnn_v2.GRU])
|
__init__.py | 158 from tensorflow.python.keras.layers.recurrent import LSTM 160 from tensorflow.python.keras.layers.recurrent_v2 import LSTM as LSTM_v2
|
wrappers_test.py | 414 rnn = keras.layers.LSTM 477 rnn = keras.layers.LSTM 503 rnn = keras.layers.LSTM 682 rnn = keras.layers.LSTM 708 rnn = keras.layers.LSTM
|
cudnn_recurrent_test.py | 266 rnn_type=['LSTM', 'GRU'], to_cudnn=[True, False], 287 if rnn_type == 'LSTM': 288 rnn_layer_class = keras.layers.LSTM 347 rnn_type=['LSTM', 'GRU'], to_cudnn=[True, False])) 367 if rnn_type == 'LSTM': 368 rnn_layer_class = keras.layers.LSTM
|
recurrent_v2.py | 39 # of LSTM and GRU. 434 @keras_export('keras.layers.LSTM', v1=[]) 435 class LSTM(recurrent.DropoutRNNCellMixin, recurrent.LSTM): 548 super(LSTM, self).__init__( 583 # LSTM does not support constants. Ignore it during process. 593 # CuDNN does not support masking, fall back to use the normal LSTM. 643 # sees multiple LSTM layers added into same graph, and it will be able 651 # Call the normal LSTM impl and register the CuDNN impl function. The 716 """LSTM with standard kernel implementation [all...] |
recurrent.py | [all...] |
recurrent_test.py | 15 """Tests for recurrent layers functionality other than GRU, LSTM, SimpleRNN. 735 layer=[rnn_v1.SimpleRNN, rnn_v1.GRU, rnn_v1.LSTM, 736 rnn_v2.GRU, rnn_v2.LSTM], [all...] |
/external/libopus/scripts/ |
dump_rnn.py | 7 from keras.layers import LSTM
|
rnn_train.py | 9 from keras.layers import LSTM
|
/external/tensorflow/tensorflow/contrib/distribute/python/ |
keras_lstm_model_correctness_test.py | 15 """Correctness tests for tf.keras LSTM model using DistributionStrategy.""" 39 lstm_embed = keras.layers.LSTM(units=4,
|
keras_stateful_lstm_model_correctness_test.py | 15 """Tests for stateful tf.keras LSTM models using DistributionStrategy.""" 60 lstm_embed = keras.layers.LSTM(units=4,
|
/external/tensorflow/tensorflow/lite/models/testdata/g3doc/ |
README.md | 74 output size of 64 (float), three Lstm layers, and one fully connected layers 84 (float), two fully connected layers, three Lstm layers, and one recurrent layer 94 It has an input size of 320 (float), an output size of 42 (float), five LSTM 108 of three embedding layer, three LSTM layers, followed by a multiplication, a 123 layer, two LSTM layers, and two additional fully-connected layers.
|
/external/tensorflow/tensorflow/python/keras/ |
integration_test.py | 121 keras.layers.LSTM(5, return_sequences=True),
|
model_subclassing_test.py | 295 self.lstm = keras.layers.LSTM(units) 298 return self.lstm(inputs) [all...] |
/external/tensorflow/tensorflow/contrib/keras/api/keras/layers/ |
__init__.py | 139 from tensorflow.python.keras.layers.recurrent import LSTM
|
/external/tensorflow/tensorflow/contrib/rnn/python/ops/ |
rnn_cell.py | 99 """Long short-term memory unit (LSTM) recurrent network cell. 106 "Learning to forget: Continual prediction with LSTM." IET, 850-855, 1999. 120 Greff et al. "LSTM: A Search Space Odyssey" 150 """Initialize the parameters for an LSTM cell. 153 num_units: int, The number of units in the LSTM cell 221 """Run one step of LSTM. 233 LSTM after reading `inputs` when previous state was `state`. 237 - Tensor(s) representing the new state of LSTM after reading `inputs` when 326 """Time-Frequency Long short-term memory unit (LSTM) recurrent network cell. 331 "Modeling Time-Frequency Patterns with LSTM vs. Convolutional Architecture [all...] |
/external/tensorflow/tensorflow/lite/experimental/examples/lstm/ |
rnn_cell.py | 161 """Long short-term memory unit (LSTM) recurrent network cell. 171 "Learning to forget: Continual prediction with LSTM." IET, 850-855, 1999. 205 """Initialize the parameters for an LSTM cell. 208 num_units: int, The number of units in the LSTM cell. 285 """Build TfLite LSTM cell graph. 386 """Run one step of LSTM. 398 LSTM after reading `inputs` when previous state was `state`. 402 - Tensor(s) representing the new state of LSTM after reading `inputs` when 448 # j output of LSTM unit.
|
/external/tensorflow/tensorflow/python/keras/saving/ |
hdf5_format_test.py | 161 (keras.layers.LSTM(output_dim)), 202 ('lstm', keras.layers.LSTM, { [all...] |
/external/tensorflow/tensorflow/contrib/seq2seq/python/kernel_tests/ |
attention_wrapper_v2_test.py | 138 encoder_output = keras.layers.LSTM(
|
/external/tensorflow/tensorflow/python/keras/engine/ |
base_layer_test.py | 628 (keras.layers.LSTM, (8, 8), collections.OrderedDict(
|
/external/tensorflow/tensorflow/python/ops/ |
rnn_cell_impl.py | 17 This module provides a number of basic commonly used RNN cells, such as LSTM 614 """Tuple used by LSTM Cells for `state_size`, `zero_state`, and output state. 636 Basic LSTM recurrent network cell. 666 """Initialize the basic LSTM cell. 669 num_units: int, The number of units in the LSTM cell. 742 """Long short-term memory cell (LSTM). 803 """Long short-term memory unit (LSTM) recurrent network cell. 810 "Learning to forget: Continual prediction with LSTM." IET, 850-855, 1999. [all...] |
/external/tensorflow/tensorflow/go/op/ |
wrappers.go | [all...] |