Searched refs:RNN (Results 1 – 25 of 69) sorted by relevance
123
| /external/tensorflow/tensorflow/core/api_def/base_api/ |
| D | api_def_CudnnRNNParamsSize.pbtxt | 3 summary: "Computes size of weights that can be used by a Cudnn RNN model."
5 Return the params size that can be used by the Cudnn RNN model. Subsequent
8 num_layers: Specifies the number of layers in the RNN model.
11 rnn_mode: Indicates the type of the RNN model.
22 initialized for this RNN model. Note that this params buffer may not be
|
| D | api_def_CudnnRNN.pbtxt | 3 summary: "A RNN backed by cuDNN."
5 Computes the RNN from the input and initial states, with respect to the params
8 rnn_mode: Indicates the type of the RNN model.
|
| D | api_def_CudnnRNNV2.pbtxt | 4 summary: "A RNN backed by cuDNN."
6 Computes the RNN from the input and initial states, with respect to the params
9 rnn_mode: Indicates the type of the RNN model.
|
| D | api_def_CudnnRNNBackpropV2.pbtxt | 6 Compute the backprop of both data and weights in a RNN. Takes an extra
7 "host_reserved" inupt than CudnnRNNBackprop, which is used to determine RNN
10 rnn_mode: Indicates the type of the RNN model.
|
| D | api_def_CudnnRNNV3.pbtxt | 4 summary: "A RNN backed by cuDNN."
6 Computes the RNN from the input and initial states, with respect to the params
9 rnn_mode: Indicates the type of the RNN model.
|
| D | api_def_CudnnRNNCanonicalToParams.pbtxt | 12 num_layers: Specifies the number of layers in the RNN model.
24 rnn_mode: Indicates the type of the RNN model.
|
| D | api_def_CudnnRNNCanonicalToParamsV2.pbtxt | 12 num_layers: Specifies the number of layers in the RNN model.
23 rnn_mode: Indicates the type of the RNN model.
|
| D | api_def_CudnnRNNParamsToCanonicalV2.pbtxt | 12 num_layers: Specifies the number of layers in the RNN model.
23 rnn_mode: Indicates the type of the RNN model.
|
| D | api_def_CudnnRNNParamsToCanonical.pbtxt | 12 num_layers: Specifies the number of layers in the RNN model.
24 rnn_mode: Indicates the type of the RNN model.
|
| D | api_def_CudnnRNNBackprop.pbtxt | 5 Compute the backprop of both data and weights in a RNN.
7 rnn_mode: Indicates the type of the RNN model.
|
| D | api_def_CudnnRNNBackpropV3.pbtxt | 6 Compute the backprop of both data and weights in a RNN. Takes an extra
9 rnn_mode: Indicates the type of the RNN model.
|
| /external/tensorflow/tensorflow/python/keras/layers/ |
| D | recurrent_test.py | 81 layer = keras.layers.RNN(cell)
94 layer = keras.layers.RNN(cells)
124 layer = keras.layers.RNN(cell)
137 layer = keras.layers.RNN(cells)
181 layer = keras.layers.RNN(cell)
196 layer = keras.layers.RNN.from_config(config)
207 layer = keras.layers.RNN(cells)
222 layer = keras.layers.RNN.from_config(config)
263 layer = keras.layers.RNN(cell)
276 layer = keras.layers.RNN(cells)
[all …]
|
| D | cudnn_recurrent.py | 30 from tensorflow.python.keras.layers.recurrent import RNN
37 class _CuDNNRNN(RNN):
65 super(RNN, self).__init__(**kwargs) # pylint: disable=bad-super-call
133 RNN, self).get_config()
154 return super(RNN, self).losses
158 RNN, self).get_losses_for(inputs=inputs)
|
| /external/tensorflow/.github/ISSUE_TEMPLATE/ |
| D | 60-tflite-converter-issue.md | 43 ### 4. (optional) RNN conversion support
44 If converting TF RNN to TFLite fused RNN ops, please prefix [RNN] in the title.
|
| /external/tensorflow/tensorflow/lite/g3doc/convert/ |
| D | rnn.md | 1 # TensorFlow RNN conversion to TensorFlow Lite
5 TensorFlow Lite supports converting TensorFlow RNN models to TensorFlow Lite’s
10 Since there are many variants of RNN APIs in TensorFlow, our approach has been
13 1. Provide **native support for standard TensorFlow RNN APIs** like Keras LSTM.
16 **user-defined** **RNN implementations** to plug in and get converted to
22 RNN interfaces.
122 ## “Bring your own TensorFlow RNN” to TensorFlow Lite
124 If a user's RNN interface is different from the standard supported ones, there
127 **Option 1:** Write adapter code in TensorFlow python to adapt the RNN interface
128 to the Keras RNN interface. This means a tf.function with
[all …]
|
| /external/rnnoise/ |
| D | rnnoise.pc.in | 9 Description: RNN-based noise suppression
|
| D | rnnoise-uninstalled.pc.in | 9 Description: RNN-based noise suppression (not installed)
|
| /external/rnnoise/doc/ |
| D | Doxyfile.in | 5 PROJECT_BRIEF = "RNN-based noise suppressor."
|
| /external/tensorflow/tensorflow/lite/g3doc/r1/convert/ |
| D | cmdline_examples.md | 365 * RNN state arrays are green. Because of the way that the converter
366 represents RNN back-edges explicitly, each RNN state is represented by a
368 * The activation array that is the source of the RNN back-edge (i.e.
369 whose contents are copied into the RNN state array after having been
373 * The actual RNN state array is
375 green</span>. It is the destination of the RNN back-edge updating
|
| /external/tensorflow/tensorflow/core/kernels/rnn/ |
| D | BUILD | 2 # OpKernels for RNN ops.
|
| /external/tensorflow/tensorflow/lite/g3doc/guide/ |
| D | roadmap.md | 22 * **LSTM / RNN support**
23 * Full LSTM and RNN conversion support, including support in Keras
|
| /external/tensorflow/tensorflow/python/keras/layers/legacy_rnn/ |
| D | BUILD | 2 # Contains the legacy TF RNN APIs (internal TensorFlow version).
|
| /external/tensorflow/tensorflow/python/ops/numpy_ops/g3doc/ |
| D | TensorFlow_NumPy_Text_Generation.ipynb | 40 "# Text generation with an RNN"
71 …"This tutorial demonstrates how to generate text using a character-based RNN. We will work with a …
363 … the next character. At the next timestep, it does the same thing but the `RNN` considers the prev…
454 "# Number of RNN units\n",
786 …em can be treated as a standard classification problem. Given the previous RNN state, and the inpu…
993 …"* It Starts by choosing a start string, initializing the RNN state and setting the number of char…
995 …"* Get the prediction distribution of the next character using the start string and the RNN state.…
999 …RNN state returned by the model is fed back into the model so that it now has more context, instea…
1069 …"You can also experiment with a different start string, or try adding another RNN layer to improve…
|
| /external/tensorflow/tensorflow/tools/api/golden/v1/ |
| D | tensorflow.keras.layers.-r-n-n.pbtxt | 1 path: "tensorflow.keras.layers.RNN"
3 is_instance: "<class \'tensorflow.python.keras.layers.recurrent.RNN\'>"
|
| /external/tensorflow/tensorflow/python/keras/benchmarks/layer_benchmarks/ |
| D | layer_benchmarks_test.py | 133 ("RNN_small_shape", tf.keras.layers.RNN,
284 tf.keras.layers.ConvLSTM2D, tf.keras.layers.GRU, tf.keras.layers.RNN,
|
123