Deploy to GitHub Pages: 7c088b52

develop/doc/_sources/howto/deep_model/rnn/index_en.rst.txt

 RNN Models
 ==========
+
+..  toctree::
+  :maxdepth: 1
+
+  rnn_config_en.rst

develop/doc/_sources/howto/deep_model/rnn/rnn_config_en.rst.txt

@@ -3,34 +3,11 @@ RNN Configuration
 
 This tutorial will guide you how to configure recurrent neural network in PaddlePaddle. PaddlePaddle supports highly flexible and efficient recurrent neural network configuration. In this tutorial, you will learn how to:
 
-- prepare sequence data for learning recurrent neural networks.
 - configure recurrent neural network architecture.
 - generate sequence with learned recurrent neural network models.
 
-We will use vanilla recurrent neural network, and sequence to sequence model to guide you through these steps. The code of sequence to sequence model can be found at :code:`demo/seqToseq`.
-
-=====================
-Prepare Sequence Data
-=====================
-
-PaddlePaddle does not need any preprocessing to sequence data, such as padding. The only thing that needs to be done is to set the type of the corresponding type to input. For example, the following code snippets defines three input. All of them are sequences, and the size of them are :code:`src_dict`, :code:`trg_dict`, and :code:`trg_dict`:
-
-.. code-block:: python
-
-    settings.input_types = [
-      integer_value_sequence(len(settings.src_dict)),
-      integer_value_sequence(len(settings.trg_dict)),
-      integer_value_sequence(len(settings.trg_dict))]
-
-
-Then at the :code:`process` function, each :code:`yield` function will return three integer lists. Each integer list is treated as a sequence of integers:
-
-.. code-block:: python
-
-    yield src_ids, trg_ids, trg_ids_next
-
-
-For more details description of how to write a data provider, please refer to :ref:`api_pydataprovider2` . The full data provider file is located at :code:`demo/seqToseq/dataprovider.py`.
+We will use vanilla recurrent neural network, and sequence to sequence model to guide you through these steps. The code of sequence to sequence model can be found at `book/08.machine_translation <https://github.com/PaddlePaddle/book/tree/develop/08.machine_translation>`_ .
+And the data preparation of this model can be found at `python/paddle/v2/dataset/wmt14.py <https://github.com/PaddlePaddle/Paddle/blob/develop/python/paddle/v2/dataset/wmt14.py>`_ 
 
 ===============================================
 Configure Recurrent Neural Network Architecture
@@ -75,19 +52,19 @@ Its **output function** simply takes :math:`x_t` as the output.
                    act=None,
                    rnn_layer_attr=None):
         def __rnn_step__(ipt):
-           out_mem = memory(name=name, size=size)
-           rnn_out = mixed_layer(input = [full_matrix_projection(ipt),
-                                          full_matrix_projection(out_mem)],
-                                 name = name,
-                                 bias_attr = rnn_bias_attr,
-                                 act = act,
-                                 layer_attr = rnn_layer_attr,
-                                 size = size)
+           out_mem = paddle.layer.memory(name=name, size=size)
+           rnn_out = paddle.layer.mixed(input = [paddle.layer.full_matrix_projection(input=ipt),
+                                                 paddle.layer.full_matrix_projection(input=out_mem)],
+                                        name = name,
+                                        bias_attr = rnn_bias_attr,
+                                        act = act,
+                                        layer_attr = rnn_layer_attr,
+                                        size = size)
            return rnn_out
-        return recurrent_group(name='%s_recurrent_group' % name,
-                               step=__rnn_step__,
-                               reverse=reverse,
-                               input=input)
+        return paddle.layer.recurrent_group(name='%s_recurrent_group' % name,
+                                            step=__rnn_step__,
+                                            reverse=reverse,
+                                            input=input)
 
 
 PaddlePaddle uses memory to construct step function. **Memory** is the most important concept when constructing recurrent neural networks in PaddlePaddle. A memory is a state that is used recurrently in step functions, such as :math:`x_{t+1} = f_x(x_t)`. One memory contains an **output** and a **input**. The output of memory at the current time step is utilized as the input of the memory at the next time step. A memory can also has a **boot layer**, whose output is utilized as the initial value of the memory. In our case, the output of the gated recurrent unit is employed as the output memory. Notice that the name of the layer :code:`rnn_out` is the same as the name of :code:`out_mem`. This means the output of the layer :code:`rnn_out` (:math:`x_{t+1}`) is utilized as the **output** of :code:`out_mem` memory.
@@ -113,43 +90,52 @@ We also project the encoder vector to :code:`decoder_size` dimensional space, ge
 .. code-block:: python
 
     # Define the data layer of the source sentence.
-    src_word_id = data_layer(name='source_language_word', size=source_dict_dim)
+    src_word_id = paddle.layer.data(
+        name='source_language_word',
+        type=paddle.data_type.integer_value_sequence(source_dict_dim))
     # Calculate the word embedding of each word.
-    src_embedding = embedding_layer(
+    src_embedding = paddle.layer.embedding(
         input=src_word_id,
         size=word_vector_dim,
-        param_attr=ParamAttr(name='_source_language_embedding'))
+        param_attr=paddle.attr.ParamAttr(name='_source_language_embedding'))
     # Apply forward recurrent neural network.
-    src_forward = grumemory(input=src_embedding, size=encoder_size)
+    src_forward = paddle.networks.simple_gru(
+        input=src_embedding, size=encoder_size)
     # Apply backward recurrent neural network. reverse=True means backward recurrent neural network.
-    src_backward = grumemory(input=src_embedding,
-                              size=encoder_size,
-                              reverse=True)
+    src_backward = paddle.networks.simple_gru(
+        input=src_embedding, size=encoder_size, reverse=True)
     # Mix the forward and backward parts of the recurrent neural network together.
-    encoded_vector = concat_layer(input=[src_forward, src_backward])
+    encoded_vector = paddle.layer.concat(input=[src_forward, src_backward])
 
     # Project encoding vector to decoder_size.
-    encoder_proj = mixed_layer(input = [full_matrix_projection(encoded_vector)],
-                               size = decoder_size)
+    encoded_proj = paddle.layer.mixed(
+        size=decoder_size,
+        input=paddle.layer.full_matrix_projection(encoded_vector))
 
     # Compute the first instance of the backward RNN.
-    backward_first = first_seq(input=src_backward)
+    backward_first = paddle.layer.first_seq(input=src_backward)
 
     # Project the first instance of backward RNN to decoder size.
-    decoder_boot = mixed_layer(input=[full_matrix_projection(backward_first)], size=decoder_size, act=TanhActivation())
+    decoder_boot = paddle.layer.mixed(
+       size=decoder_size,
+       act=paddle.activation.Tanh(),
+       input=paddle.layer.full_matrix_projection(backward_first))
 
 
 The decoder uses :code:`recurrent_group` to define the recurrent neural network. The step and output functions are defined in :code:`gru_decoder_with_attention`:
 
 .. code-block:: python
 
-    group_inputs=[StaticInput(input=encoded_vector,is_seq=True),
-                  StaticInput(input=encoded_proj,is_seq=True)]
-    trg_embedding = embedding_layer(
-        input=data_layer(name='target_language_word',
-                         size=target_dict_dim),
-        size=word_vector_dim,
-        param_attr=ParamAttr(name='_target_language_embedding'))
+    group_input1 = paddle.layer.StaticInput(input=encoded_vector, is_seq=True)
+    group_input2 = paddle.layer.StaticInput(input=encoded_proj, is_seq=True)
+    group_inputs = [group_input1, group_input2]
+    trg_embedding = paddle.layer.embedding(
+            input=paddle.layer.data(
+                name='target_language_word',
+                type=paddle.data_type.integer_value_sequence(target_dict_dim)),
+            size=word_vector_dim,
+            param_attr=paddle.attr.ParamAttr(name='_target_language_embedding'))
+        group_inputs.append(trg_embedding)
     group_inputs.append(trg_embedding)
 
     # For decoder equipped with attention mechanism, in training,
@@ -158,9 +144,10 @@ The decoder uses :code:`recurrent_group` to define the recurrent neural network.
     # StaticInput means the same value is utilized at different time steps.
     # Otherwise, it is a sequence input. Inputs at different time steps are different.
     # All sequence inputs should have the same length.
-    decoder = recurrent_group(name=decoder_group_name,
-                              step=gru_decoder_with_attention,
-                              input=group_inputs)
+    decoder = paddle.layer.recurrent_group(
+            name=decoder_group_name,
+            step=gru_decoder_with_attention,
+            input=group_inputs)
 
 
 The implementation of the step function is listed as below. First, it defines the **memory** of the decoder network. Then it defines attention, gated recurrent unit step function, and the output function:
@@ -171,27 +158,32 @@ The implementation of the step function is listed as below. First, it defines th
         # Defines the memory of the decoder.
         # The output of this memory is defined in gru_step.
         # Notice that the name of gru_step should be the same as the name of this memory.
-        decoder_mem = memory(name='gru_decoder',
-                             size=decoder_size,
-                             boot_layer=decoder_boot)
+        decoder_mem = paddle.layer.memory(
+            name='gru_decoder', size=decoder_size, boot_layer=decoder_boot)
         # Compute attention weighted encoder vector.
-        context = simple_attention(encoded_sequence=enc_vec,
-                                   encoded_proj=enc_proj,
-                                   decoder_state=decoder_mem)
+        context = paddle.networks.simple_attention(
+            encoded_sequence=enc_vec,
+            encoded_proj=enc_proj,
+            decoder_state=decoder_mem)
         # Mix the current word embedding and the attention weighted encoder vector.
-        decoder_inputs = mixed_layer(inputs = [full_matrix_projection(context),
-                                               full_matrix_projection(current_word)],
-                                     size = decoder_size * 3)
+        decoder_inputs = paddle.layer.mixed(
+            size=decoder_size * 3,
+            input=[
+                paddle.layer.full_matrix_projection(input=context),
+                paddle.layer.full_matrix_projection(input=current_word)
+            ])
         # Define Gated recurrent unit recurrent neural network step function.
-        gru_step = gru_step_layer(name='gru_decoder',
-                                  input=decoder_inputs,
-                                  output_mem=decoder_mem,
-                                  size=decoder_size)
+        gru_step = paddle.layer.gru_step(
+            name='gru_decoder',
+            input=decoder_inputs,
+            output_mem=decoder_mem,
+            size=decoder_size)
         # Defines the output function.
-        out = mixed_layer(input=[full_matrix_projection(input=gru_step)],
-                          size=target_dict_dim,
-                          bias_attr=True,
-                          act=SoftmaxActivation())
+        out = paddle.layer.mixed(
+            size=target_dict_dim,
+            bias_attr=True,
+            act=paddle.activation.Softmax(),
+            input=paddle.layer.full_matrix_projection(input=gru_step))
         return out
 
 
@@ -207,45 +199,37 @@ After training the model, we can use it to generate sequences. A common practice
   - :code:`eos_id`: the end token. Every sentence ends with the end token.
   - :code:`beam_size`: the beam size used in beam search.
   - :code:`max_length`: the maximum length of the generated sentences.
-
-* use :code:`seqtext_printer_evaluator` to print text according to index matrix and dictionary. This function needs to set:
-
-  - :code:`id_input`: the integer ID of the data, used to identify the corresponding output in the generated files.
-  - :code:`dict_file`: the dictionary file for converting word id to word.
-  - :code:`result_file`: the path of the generation result file.
     
 The code is listed below:
 
 .. code-block:: python
 
-    group_inputs=[StaticInput(input=encoded_vector,is_seq=True),
-                  StaticInput(input=encoded_proj,is_seq=True)]
+    group_input1 = paddle.layer.StaticInput(input=encoded_vector, is_seq=True)
+    group_input2 = paddle.layer.StaticInput(input=encoded_proj, is_seq=True)
+    group_inputs = [group_input1, group_input2]
     # In generation, decoder predicts a next target word based on
     # the encoded source sequence and the last generated target word.
     # The encoded source sequence (encoder's output) must be specified by
     # StaticInput which is a read-only memory.
     # Here, GeneratedInputs automatically fetchs the last generated word,
     # which is initialized by a start mark, such as <s>.
-    trg_embedding = GeneratedInput(
-        size=target_dict_dim,
-        embedding_name='_target_language_embedding',
-        embedding_size=word_vector_dim)
+    trg_embedding = paddle.layer.GeneratedInput(
+            size=target_dict_dim,
+            embedding_name='_target_language_embedding',
+            embedding_size=word_vector_dim)
     group_inputs.append(trg_embedding)
-    beam_gen = beam_search(name=decoder_group_name,
-                           step=gru_decoder_with_attention,
-                           input=group_inputs,
-                           bos_id=0, # Beginnning token.
-                           eos_id=1, # End of sentence token.
-                           beam_size=beam_size,
-                           max_length=max_length)
+    beam_gen = paddle.layer.beam_search(
+            name=decoder_group_name,
+            step=gru_decoder_with_attention,
+            input=group_inputs,
+            bos_id=0, # Beginnning token.
+            eos_id=1, # End of sentence token.
+            beam_size=beam_size,
+            max_length=max_length)
 
-    seqtext_printer_evaluator(input=beam_gen,
-                              id_input=data_layer(name="sent_id", size=1),
-                              dict_file=trg_dict_path,
-                              result_file=gen_trans_file)
-    outputs(beam_gen)
+    return beam_gen
 
 
-Notice that this generation technique is only useful for decoder like generation process. If you are working on sequence tagging tasks, please refer to :ref:`semantic_role_labeling` for more details.
+Notice that this generation technique is only useful for decoder like generation process. If you are working on sequence tagging tasks, please refer to `book/06.understand_sentiment <https://github.com/PaddlePaddle/book/tree/develop/06.understand_sentiment>`_ for more details.
 
-The full configuration file is located at :code:`demo/seqToseq/seqToseq_net.py`.
+The full configuration file is located at `book/08.machine_translation/train.py <https://github.com/PaddlePaddle/book/blob/develop/08.machine_translation/train.py>`_ .

develop/doc/about/index_en.html

@@ -128,7 +128,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/api/index_en.html

@@ -129,7 +129,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/api/v1/data_provider/dataprovider_en.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/api/v1/data_provider/pydataprovider2_en.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/api/v1/index_en.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/api/v1/predict/swig_py_paddle_en.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/api/v2/config/activation.html

@@ -130,7 +130,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/api/v2/config/attr.html

@@ -130,7 +130,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/api/v2/config/evaluators.html

@@ -130,7 +130,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/api/v2/config/layer.html

@@ -130,7 +130,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/api/v2/config/networks.html

@@ -130,7 +130,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/api/v2/config/optimizer.html

@@ -130,7 +130,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/api/v2/config/pooling.html

@@ -130,7 +130,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/api/v2/data.html

@@ -130,7 +130,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/api/v2/model_configs.html

@@ -130,7 +130,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/api/v2/run_logic.html

@@ -130,7 +130,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/design/api.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/design/build_system/README.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/design/cluster_train/README.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/design/cluster_train/checkpointing.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/design/cluster_train/data_dispatch.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/design/cluster_train/master_server.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/design/cluster_train/pserver_client.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/design/cluster_train/remote_parameter_updater.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/design/cluster_train/submit-job.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/design/file_manager/README.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/design/file_manager/pfs/pfsclient.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/design/multi_language_interface/00.why_plain_c.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/design/multi_language_interface/01.inference_implementation.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/design/parameters_in_cpp.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/design/reader/README.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/design/releasing_process.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/genindex.html

@@ -128,7 +128,10 @@
 <li class="toctree-l2"><a class="reference internal" href="howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/getstarted/basic_usage/index_en.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/getstarted/build_and_install/build_from_source_en.html

@@ -130,7 +130,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/getstarted/build_and_install/docker_install_en.html

@@ -130,7 +130,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/getstarted/build_and_install/index_en.html

@@ -130,7 +130,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/getstarted/build_and_install/ubuntu_install_en.html

@@ -130,7 +130,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/getstarted/index_en.html

@@ -129,7 +129,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/howto/deep_model/rnn/index_en.html

@@ -34,7 +34,7 @@
         <link rel="search" title="Search" href="../../../search.html"/>
     <link rel="top" title="PaddlePaddle  documentation" href="../../../index.html"/>
         <link rel="up" title="HOW TO" href="../../index_en.html"/>
-        <link rel="next" title="Tune GPU Performance" href="../../optimization/gpu_profiling_en.html"/>
+        <link rel="next" title="RNN Configuration" href="rnn_config_en.html"/>
         <link rel="prev" title="Contribute Code" href="../../dev/contribute_to_paddle_en.html"/> 
 
   <link rel="stylesheet" href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" type="text/css" />
@@ -130,7 +130,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2 current"><a class="current reference internal" href="#">RNN Models</a></li>
+<li class="toctree-l2 current"><a class="current reference internal" href="#">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>
@@ -183,6 +186,11 @@
             
   <div class="section" id="rnn-models">
 <h1>RNN Models<a class="headerlink" href="#rnn-models" title="Permalink to this headline">¶</a></h1>
+<div class="toctree-wrapper compound">
+<ul>
+<li class="toctree-l1"><a class="reference internal" href="rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</div>
 </div>
 
 
@@ -192,7 +200,7 @@
   
     <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
       
-        <a href="../../optimization/gpu_profiling_en.html" class="btn btn-neutral float-right" title="Tune GPU Performance" accesskey="n">Next <span class="fa fa-arrow-circle-right"></span></a>
+        <a href="rnn_config_en.html" class="btn btn-neutral float-right" title="RNN Configuration" accesskey="n">Next <span class="fa fa-arrow-circle-right"></span></a>
       
       
         <a href="../../dev/contribute_to_paddle_en.html" class="btn btn-neutral" title="Contribute Code" accesskey="p"><span class="fa fa-arrow-circle-left"></span> Previous</a>

develop/doc/howto/deep_model/rnn/rnn_config_en.html

@@ -32,7 +32,10 @@
         <link rel="index" title="Index"
               href="../../../genindex.html"/>
         <link rel="search" title="Search" href="../../../search.html"/>
-    <link rel="top" title="PaddlePaddle  documentation" href="../../../index.html"/> 
+    <link rel="top" title="PaddlePaddle  documentation" href="../../../index.html"/>
+        <link rel="up" title="RNN Models" href="index_en.html"/>
+        <link rel="next" title="Tune GPU Performance" href="../../optimization/gpu_profiling_en.html"/>
+        <link rel="prev" title="RNN Models" href="index_en.html"/> 
 
   <link rel="stylesheet" href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" type="text/css" />
   <link rel="stylesheet" href="../../../_static/css/override.css" type="text/css" />
@@ -80,9 +83,9 @@
       </div>
       <div class="doc-module">
         
-        <ul>
+        <ul class="current">
 <li class="toctree-l1"><a class="reference internal" href="../../../getstarted/index_en.html">GET STARTED</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../index_en.html">HOW TO</a></li>
+<li class="toctree-l1 current"><a class="reference internal" href="../../index_en.html">HOW TO</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../api/index_en.html">API</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../about/index_en.html">ABOUT</a></li>
 </ul>
@@ -105,7 +108,7 @@
     <nav class="doc-menu-vertical" role="navigation">
         
           
-          <ul>
+          <ul class="current">
 <li class="toctree-l1"><a class="reference internal" href="../../../getstarted/index_en.html">GET STARTED</a><ul>
 <li class="toctree-l2"><a class="reference internal" href="../../../getstarted/build_and_install/index_en.html">Install and Build</a><ul>
 <li class="toctree-l3"><a class="reference internal" href="../../../getstarted/build_and_install/docker_install_en.html">PaddlePaddle in Docker Containers</a></li>
@@ -115,7 +118,7 @@
 </li>
 </ul>
 </li>
-<li class="toctree-l1"><a class="reference internal" href="../../index_en.html">HOW TO</a><ul>
+<li class="toctree-l1 current"><a class="reference internal" href="../../index_en.html">HOW TO</a><ul class="current">
 <li class="toctree-l2"><a class="reference internal" href="../../usage/cmd_parameter/index_en.html">Set Command-line Parameters</a><ul>
 <li class="toctree-l3"><a class="reference internal" href="../../usage/cmd_parameter/use_case_en.html">Use Case</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../usage/cmd_parameter/arguments_en.html">Argument Outline</a></li>
@@ -127,7 +130,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="index_en.html">RNN Models</a></li>
+<li class="toctree-l2 current"><a class="reference internal" href="index_en.html">RNN Models</a><ul class="current">
+<li class="toctree-l3 current"><a class="current reference internal" href="#">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>
@@ -167,6 +173,10 @@
 <div role="navigation" aria-label="breadcrumbs navigation">
   <ul class="wy-breadcrumbs">
       
+        <li><a href="../../index_en.html">HOW TO</a> > </li>
+      
+        <li><a href="index_en.html">RNN Models</a> > </li>
+      
     <li>RNN Configuration</li>
   </ul>
 </div>
@@ -180,26 +190,11 @@
 <h1>RNN Configuration<a class="headerlink" href="#rnn-configuration" title="Permalink to this headline">¶</a></h1>
 <p>This tutorial will guide you how to configure recurrent neural network in PaddlePaddle. PaddlePaddle supports highly flexible and efficient recurrent neural network configuration. In this tutorial, you will learn how to:</p>
 <ul class="simple">
-<li>prepare sequence data for learning recurrent neural networks.</li>
 <li>configure recurrent neural network architecture.</li>
 <li>generate sequence with learned recurrent neural network models.</li>
 </ul>
-<p>We will use vanilla recurrent neural network, and sequence to sequence model to guide you through these steps. The code of sequence to sequence model can be found at <code class="code docutils literal"><span class="pre">demo/seqToseq</span></code>.</p>
-<div class="section" id="prepare-sequence-data">
-<h2>Prepare Sequence Data<a class="headerlink" href="#prepare-sequence-data" title="Permalink to this headline">¶</a></h2>
-<p>PaddlePaddle does not need any preprocessing to sequence data, such as padding. The only thing that needs to be done is to set the type of the corresponding type to input. For example, the following code snippets defines three input. All of them are sequences, and the size of them are <code class="code docutils literal"><span class="pre">src_dict</span></code>, <code class="code docutils literal"><span class="pre">trg_dict</span></code>, and <code class="code docutils literal"><span class="pre">trg_dict</span></code>:</p>
-<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">settings</span><span class="o">.</span><span class="n">input_types</span> <span class="o">=</span> <span class="p">[</span>
-  <span class="n">integer_value_sequence</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">settings</span><span class="o">.</span><span class="n">src_dict</span><span class="p">)),</span>
-  <span class="n">integer_value_sequence</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">settings</span><span class="o">.</span><span class="n">trg_dict</span><span class="p">)),</span>
-  <span class="n">integer_value_sequence</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">settings</span><span class="o">.</span><span class="n">trg_dict</span><span class="p">))]</span>
-</pre></div>
-</div>
-<p>Then at the <code class="code docutils literal"><span class="pre">process</span></code> function, each <code class="code docutils literal"><span class="pre">yield</span></code> function will return three integer lists. Each integer list is treated as a sequence of integers:</p>
-<div class="highlight-python"><div class="highlight"><pre><span></span><span class="k">yield</span> <span class="n">src_ids</span><span class="p">,</span> <span class="n">trg_ids</span><span class="p">,</span> <span class="n">trg_ids_next</span>
-</pre></div>
-</div>
-<p>For more details description of how to write a data provider, please refer to <a class="reference internal" href="../../../api/v1/data_provider/pydataprovider2_en.html#api-pydataprovider2"><span class="std std-ref">PyDataProvider2</span></a> . The full data provider file is located at <code class="code docutils literal"><span class="pre">demo/seqToseq/dataprovider.py</span></code>.</p>
-</div>
+<p>We will use vanilla recurrent neural network, and sequence to sequence model to guide you through these steps. The code of sequence to sequence model can be found at <a class="reference external" href="https://github.com/PaddlePaddle/book/tree/develop/08.machine_translation">book/08.machine_translation</a> .
+And the data preparation of this model can be found at <a class="reference external" href="https://github.com/PaddlePaddle/Paddle/blob/develop/python/paddle/v2/dataset/wmt14.py">python/paddle/v2/dataset/wmt14.py</a></p>
 <div class="section" id="configure-recurrent-neural-network-architecture">
 <h2>Configure Recurrent Neural Network Architecture<a class="headerlink" href="#configure-recurrent-neural-network-architecture" title="Permalink to this headline">¶</a></h2>
 <div class="section" id="simple-gated-recurrent-neural-network">
@@ -224,19 +219,19 @@ Its <strong>output function</strong> simply takes <span class="math">\(x_t\)</sp
                <span class="n">act</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span>
                <span class="n">rnn_layer_attr</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
     <span class="k">def</span> <span class="nf">__rnn_step__</span><span class="p">(</span><span class="n">ipt</span><span class="p">):</span>
-       <span class="n">out_mem</span> <span class="o">=</span> <span class="n">memory</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="n">name</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="n">size</span><span class="p">)</span>
-       <span class="n">rnn_out</span> <span class="o">=</span> <span class="n">mixed_layer</span><span class="p">(</span><span class="nb">input</span> <span class="o">=</span> <span class="p">[</span><span class="n">full_matrix_projection</span><span class="p">(</span><span class="n">ipt</span><span class="p">),</span>
-                                      <span class="n">full_matrix_projection</span><span class="p">(</span><span class="n">out_mem</span><span class="p">)],</span>
-                             <span class="n">name</span> <span class="o">=</span> <span class="n">name</span><span class="p">,</span>
-                             <span class="n">bias_attr</span> <span class="o">=</span> <span class="n">rnn_bias_attr</span><span class="p">,</span>
-                             <span class="n">act</span> <span class="o">=</span> <span class="n">act</span><span class="p">,</span>
-                             <span class="n">layer_attr</span> <span class="o">=</span> <span class="n">rnn_layer_attr</span><span class="p">,</span>
-                             <span class="n">size</span> <span class="o">=</span> <span class="n">size</span><span class="p">)</span>
+       <span class="n">out_mem</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">memory</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="n">name</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="n">size</span><span class="p">)</span>
+       <span class="n">rnn_out</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">mixed</span><span class="p">(</span><span class="nb">input</span> <span class="o">=</span> <span class="p">[</span><span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">full_matrix_projection</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">ipt</span><span class="p">),</span>
+                                             <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">full_matrix_projection</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">out_mem</span><span class="p">)],</span>
+                                    <span class="n">name</span> <span class="o">=</span> <span class="n">name</span><span class="p">,</span>
+                                    <span class="n">bias_attr</span> <span class="o">=</span> <span class="n">rnn_bias_attr</span><span class="p">,</span>
+                                    <span class="n">act</span> <span class="o">=</span> <span class="n">act</span><span class="p">,</span>
+                                    <span class="n">layer_attr</span> <span class="o">=</span> <span class="n">rnn_layer_attr</span><span class="p">,</span>
+                                    <span class="n">size</span> <span class="o">=</span> <span class="n">size</span><span class="p">)</span>
        <span class="k">return</span> <span class="n">rnn_out</span>
-    <span class="k">return</span> <span class="n">recurrent_group</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;</span><span class="si">%s</span><span class="s1">_recurrent_group&#39;</span> <span class="o">%</span> <span class="n">name</span><span class="p">,</span>
-                           <span class="n">step</span><span class="o">=</span><span class="n">__rnn_step__</span><span class="p">,</span>
-                           <span class="n">reverse</span><span class="o">=</span><span class="n">reverse</span><span class="p">,</span>
-                           <span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">)</span>
+    <span class="k">return</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">recurrent_group</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;</span><span class="si">%s</span><span class="s1">_recurrent_group&#39;</span> <span class="o">%</span> <span class="n">name</span><span class="p">,</span>
+                                        <span class="n">step</span><span class="o">=</span><span class="n">__rnn_step__</span><span class="p">,</span>
+                                        <span class="n">reverse</span><span class="o">=</span><span class="n">reverse</span><span class="p">,</span>
+                                        <span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">)</span>
 </pre></div>
 </div>
 <p>PaddlePaddle uses memory to construct step function. <strong>Memory</strong> is the most important concept when constructing recurrent neural networks in PaddlePaddle. A memory is a state that is used recurrently in step functions, such as <span class="math">\(x_{t+1} = f_x(x_t)\)</span>. One memory contains an <strong>output</strong> and a <strong>input</strong>. The output of memory at the current time step is utilized as the input of the memory at the next time step. A memory can also has a <strong>boot layer</strong>, whose output is utilized as the initial value of the memory. In our case, the output of the gated recurrent unit is employed as the output memory. Notice that the name of the layer <code class="code docutils literal"><span class="pre">rnn_out</span></code> is the same as the name of <code class="code docutils literal"><span class="pre">out_mem</span></code>. This means the output of the layer <code class="code docutils literal"><span class="pre">rnn_out</span></code> (<span class="math">\(x_{t+1}\)</span>) is utilized as the <strong>output</strong> of <code class="code docutils literal"><span class="pre">out_mem</span></code> memory.</p>
@@ -251,40 +246,49 @@ Its <strong>output function</strong> simply takes <span class="math">\(x_t\)</sp
 <p>The encoder part of the model is listed below. It calls <code class="code docutils literal"><span class="pre">grumemory</span></code> to represent gated recurrent neural network. It is the recommended way of using recurrent neural network if the network architecture is simple, because it is faster than <code class="code docutils literal"><span class="pre">recurrent_group</span></code>. We have implemented most of the commonly used recurrent neural network architectures, you can refer to <span class="xref std std-ref">api_trainer_config_helpers_layers</span> for more details.</p>
 <p>We also project the encoder vector to <code class="code docutils literal"><span class="pre">decoder_size</span></code> dimensional space, get the first instance of the backward recurrent network, and project it to <code class="code docutils literal"><span class="pre">decoder_size</span></code> dimensional space:</p>
 <div class="highlight-python"><div class="highlight"><pre><span></span><span class="c1"># Define the data layer of the source sentence.</span>
-<span class="n">src_word_id</span> <span class="o">=</span> <span class="n">data_layer</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;source_language_word&#39;</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="n">source_dict_dim</span><span class="p">)</span>
+<span class="n">src_word_id</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">data</span><span class="p">(</span>
+    <span class="n">name</span><span class="o">=</span><span class="s1">&#39;source_language_word&#39;</span><span class="p">,</span>
+    <span class="nb">type</span><span class="o">=</span><span class="n">paddle</span><span class="o">.</span><span class="n">data_type</span><span class="o">.</span><span class="n">integer_value_sequence</span><span class="p">(</span><span class="n">source_dict_dim</span><span class="p">))</span>
 <span class="c1"># Calculate the word embedding of each word.</span>
-<span class="n">src_embedding</span> <span class="o">=</span> <span class="n">embedding_layer</span><span class="p">(</span>
+<span class="n">src_embedding</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">embedding</span><span class="p">(</span>
     <span class="nb">input</span><span class="o">=</span><span class="n">src_word_id</span><span class="p">,</span>
     <span class="n">size</span><span class="o">=</span><span class="n">word_vector_dim</span><span class="p">,</span>
-    <span class="n">param_attr</span><span class="o">=</span><span class="n">ParamAttr</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;_source_language_embedding&#39;</span><span class="p">))</span>
+    <span class="n">param_attr</span><span class="o">=</span><span class="n">paddle</span><span class="o">.</span><span class="n">attr</span><span class="o">.</span><span class="n">ParamAttr</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;_source_language_embedding&#39;</span><span class="p">))</span>
 <span class="c1"># Apply forward recurrent neural network.</span>
-<span class="n">src_forward</span> <span class="o">=</span> <span class="n">grumemory</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">src_embedding</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="n">encoder_size</span><span class="p">)</span>
+<span class="n">src_forward</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">networks</span><span class="o">.</span><span class="n">simple_gru</span><span class="p">(</span>
+    <span class="nb">input</span><span class="o">=</span><span class="n">src_embedding</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="n">encoder_size</span><span class="p">)</span>
 <span class="c1"># Apply backward recurrent neural network. reverse=True means backward recurrent neural network.</span>
-<span class="n">src_backward</span> <span class="o">=</span> <span class="n">grumemory</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">src_embedding</span><span class="p">,</span>
-                          <span class="n">size</span><span class="o">=</span><span class="n">encoder_size</span><span class="p">,</span>
-                          <span class="n">reverse</span><span class="o">=</span><span class="bp">True</span><span class="p">)</span>
+<span class="n">src_backward</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">networks</span><span class="o">.</span><span class="n">simple_gru</span><span class="p">(</span>
+    <span class="nb">input</span><span class="o">=</span><span class="n">src_embedding</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="n">encoder_size</span><span class="p">,</span> <span class="n">reverse</span><span class="o">=</span><span class="bp">True</span><span class="p">)</span>
 <span class="c1"># Mix the forward and backward parts of the recurrent neural network together.</span>
-<span class="n">encoded_vector</span> <span class="o">=</span> <span class="n">concat_layer</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="p">[</span><span class="n">src_forward</span><span class="p">,</span> <span class="n">src_backward</span><span class="p">])</span>
+<span class="n">encoded_vector</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">concat</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="p">[</span><span class="n">src_forward</span><span class="p">,</span> <span class="n">src_backward</span><span class="p">])</span>
 
 <span class="c1"># Project encoding vector to decoder_size.</span>
-<span class="n">encoder_proj</span> <span class="o">=</span> <span class="n">mixed_layer</span><span class="p">(</span><span class="nb">input</span> <span class="o">=</span> <span class="p">[</span><span class="n">full_matrix_projection</span><span class="p">(</span><span class="n">encoded_vector</span><span class="p">)],</span>
-                           <span class="n">size</span> <span class="o">=</span> <span class="n">decoder_size</span><span class="p">)</span>
+<span class="n">encoded_proj</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">mixed</span><span class="p">(</span>
+    <span class="n">size</span><span class="o">=</span><span class="n">decoder_size</span><span class="p">,</span>
+    <span class="nb">input</span><span class="o">=</span><span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">full_matrix_projection</span><span class="p">(</span><span class="n">encoded_vector</span><span class="p">))</span>
 
 <span class="c1"># Compute the first instance of the backward RNN.</span>
-<span class="n">backward_first</span> <span class="o">=</span> <span class="n">first_seq</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">src_backward</span><span class="p">)</span>
+<span class="n">backward_first</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">first_seq</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">src_backward</span><span class="p">)</span>
 
 <span class="c1"># Project the first instance of backward RNN to decoder size.</span>
-<span class="n">decoder_boot</span> <span class="o">=</span> <span class="n">mixed_layer</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="p">[</span><span class="n">full_matrix_projection</span><span class="p">(</span><span class="n">backward_first</span><span class="p">)],</span> <span class="n">size</span><span class="o">=</span><span class="n">decoder_size</span><span class="p">,</span> <span class="n">act</span><span class="o">=</span><span class="n">TanhActivation</span><span class="p">())</span>
+<span class="n">decoder_boot</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">mixed</span><span class="p">(</span>
+   <span class="n">size</span><span class="o">=</span><span class="n">decoder_size</span><span class="p">,</span>
+   <span class="n">act</span><span class="o">=</span><span class="n">paddle</span><span class="o">.</span><span class="n">activation</span><span class="o">.</span><span class="n">Tanh</span><span class="p">(),</span>
+   <span class="nb">input</span><span class="o">=</span><span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">full_matrix_projection</span><span class="p">(</span><span class="n">backward_first</span><span class="p">))</span>
 </pre></div>
 </div>
 <p>The decoder uses <code class="code docutils literal"><span class="pre">recurrent_group</span></code> to define the recurrent neural network. The step and output functions are defined in <code class="code docutils literal"><span class="pre">gru_decoder_with_attention</span></code>:</p>
-<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">group_inputs</span><span class="o">=</span><span class="p">[</span><span class="n">StaticInput</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">encoded_vector</span><span class="p">,</span><span class="n">is_seq</span><span class="o">=</span><span class="bp">True</span><span class="p">),</span>
-              <span class="n">StaticInput</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">encoded_proj</span><span class="p">,</span><span class="n">is_seq</span><span class="o">=</span><span class="bp">True</span><span class="p">)]</span>
-<span class="n">trg_embedding</span> <span class="o">=</span> <span class="n">embedding_layer</span><span class="p">(</span>
-    <span class="nb">input</span><span class="o">=</span><span class="n">data_layer</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;target_language_word&#39;</span><span class="p">,</span>
-                     <span class="n">size</span><span class="o">=</span><span class="n">target_dict_dim</span><span class="p">),</span>
-    <span class="n">size</span><span class="o">=</span><span class="n">word_vector_dim</span><span class="p">,</span>
-    <span class="n">param_attr</span><span class="o">=</span><span class="n">ParamAttr</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;_target_language_embedding&#39;</span><span class="p">))</span>
+<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">group_input1</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">StaticInput</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">encoded_vector</span><span class="p">,</span> <span class="n">is_seq</span><span class="o">=</span><span class="bp">True</span><span class="p">)</span>
+<span class="n">group_input2</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">StaticInput</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">encoded_proj</span><span class="p">,</span> <span class="n">is_seq</span><span class="o">=</span><span class="bp">True</span><span class="p">)</span>
+<span class="n">group_inputs</span> <span class="o">=</span> <span class="p">[</span><span class="n">group_input1</span><span class="p">,</span> <span class="n">group_input2</span><span class="p">]</span>
+<span class="n">trg_embedding</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">embedding</span><span class="p">(</span>
+        <span class="nb">input</span><span class="o">=</span><span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">data</span><span class="p">(</span>
+            <span class="n">name</span><span class="o">=</span><span class="s1">&#39;target_language_word&#39;</span><span class="p">,</span>
+            <span class="nb">type</span><span class="o">=</span><span class="n">paddle</span><span class="o">.</span><span class="n">data_type</span><span class="o">.</span><span class="n">integer_value_sequence</span><span class="p">(</span><span class="n">target_dict_dim</span><span class="p">)),</span>
+        <span class="n">size</span><span class="o">=</span><span class="n">word_vector_dim</span><span class="p">,</span>
+        <span class="n">param_attr</span><span class="o">=</span><span class="n">paddle</span><span class="o">.</span><span class="n">attr</span><span class="o">.</span><span class="n">ParamAttr</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;_target_language_embedding&#39;</span><span class="p">))</span>
+    <span class="n">group_inputs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">trg_embedding</span><span class="p">)</span>
 <span class="n">group_inputs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">trg_embedding</span><span class="p">)</span>
 
 <span class="c1"># For decoder equipped with attention mechanism, in training,</span>
@@ -293,9 +297,10 @@ Its <strong>output function</strong> simply takes <span class="math">\(x_t\)</sp
 <span class="c1"># StaticInput means the same value is utilized at different time steps.</span>
 <span class="c1"># Otherwise, it is a sequence input. Inputs at different time steps are different.</span>
 <span class="c1"># All sequence inputs should have the same length.</span>
-<span class="n">decoder</span> <span class="o">=</span> <span class="n">recurrent_group</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="n">decoder_group_name</span><span class="p">,</span>
-                          <span class="n">step</span><span class="o">=</span><span class="n">gru_decoder_with_attention</span><span class="p">,</span>
-                          <span class="nb">input</span><span class="o">=</span><span class="n">group_inputs</span><span class="p">)</span>
+<span class="n">decoder</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">recurrent_group</span><span class="p">(</span>
+        <span class="n">name</span><span class="o">=</span><span class="n">decoder_group_name</span><span class="p">,</span>
+        <span class="n">step</span><span class="o">=</span><span class="n">gru_decoder_with_attention</span><span class="p">,</span>
+        <span class="nb">input</span><span class="o">=</span><span class="n">group_inputs</span><span class="p">)</span>
 </pre></div>
 </div>
 <p>The implementation of the step function is listed as below. First, it defines the <strong>memory</strong> of the decoder network. Then it defines attention, gated recurrent unit step function, and the output function:</p>
@@ -303,27 +308,32 @@ Its <strong>output function</strong> simply takes <span class="math">\(x_t\)</sp
     <span class="c1"># Defines the memory of the decoder.</span>
     <span class="c1"># The output of this memory is defined in gru_step.</span>
     <span class="c1"># Notice that the name of gru_step should be the same as the name of this memory.</span>
-    <span class="n">decoder_mem</span> <span class="o">=</span> <span class="n">memory</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;gru_decoder&#39;</span><span class="p">,</span>
-                         <span class="n">size</span><span class="o">=</span><span class="n">decoder_size</span><span class="p">,</span>
-                         <span class="n">boot_layer</span><span class="o">=</span><span class="n">decoder_boot</span><span class="p">)</span>
+    <span class="n">decoder_mem</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">memory</span><span class="p">(</span>
+        <span class="n">name</span><span class="o">=</span><span class="s1">&#39;gru_decoder&#39;</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="n">decoder_size</span><span class="p">,</span> <span class="n">boot_layer</span><span class="o">=</span><span class="n">decoder_boot</span><span class="p">)</span>
     <span class="c1"># Compute attention weighted encoder vector.</span>
-    <span class="n">context</span> <span class="o">=</span> <span class="n">simple_attention</span><span class="p">(</span><span class="n">encoded_sequence</span><span class="o">=</span><span class="n">enc_vec</span><span class="p">,</span>
-                               <span class="n">encoded_proj</span><span class="o">=</span><span class="n">enc_proj</span><span class="p">,</span>
-                               <span class="n">decoder_state</span><span class="o">=</span><span class="n">decoder_mem</span><span class="p">)</span>
+    <span class="n">context</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">networks</span><span class="o">.</span><span class="n">simple_attention</span><span class="p">(</span>
+        <span class="n">encoded_sequence</span><span class="o">=</span><span class="n">enc_vec</span><span class="p">,</span>
+        <span class="n">encoded_proj</span><span class="o">=</span><span class="n">enc_proj</span><span class="p">,</span>
+        <span class="n">decoder_state</span><span class="o">=</span><span class="n">decoder_mem</span><span class="p">)</span>
     <span class="c1"># Mix the current word embedding and the attention weighted encoder vector.</span>
-    <span class="n">decoder_inputs</span> <span class="o">=</span> <span class="n">mixed_layer</span><span class="p">(</span><span class="n">inputs</span> <span class="o">=</span> <span class="p">[</span><span class="n">full_matrix_projection</span><span class="p">(</span><span class="n">context</span><span class="p">),</span>
-                                           <span class="n">full_matrix_projection</span><span class="p">(</span><span class="n">current_word</span><span class="p">)],</span>
-                                 <span class="n">size</span> <span class="o">=</span> <span class="n">decoder_size</span> <span class="o">*</span> <span class="mi">3</span><span class="p">)</span>
+    <span class="n">decoder_inputs</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">mixed</span><span class="p">(</span>
+        <span class="n">size</span><span class="o">=</span><span class="n">decoder_size</span> <span class="o">*</span> <span class="mi">3</span><span class="p">,</span>
+        <span class="nb">input</span><span class="o">=</span><span class="p">[</span>
+            <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">full_matrix_projection</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">context</span><span class="p">),</span>
+            <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">full_matrix_projection</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">current_word</span><span class="p">)</span>
+        <span class="p">])</span>
     <span class="c1"># Define Gated recurrent unit recurrent neural network step function.</span>
-    <span class="n">gru_step</span> <span class="o">=</span> <span class="n">gru_step_layer</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;gru_decoder&#39;</span><span class="p">,</span>
-                              <span class="nb">input</span><span class="o">=</span><span class="n">decoder_inputs</span><span class="p">,</span>
-                              <span class="n">output_mem</span><span class="o">=</span><span class="n">decoder_mem</span><span class="p">,</span>
-                              <span class="n">size</span><span class="o">=</span><span class="n">decoder_size</span><span class="p">)</span>
+    <span class="n">gru_step</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">gru_step</span><span class="p">(</span>
+        <span class="n">name</span><span class="o">=</span><span class="s1">&#39;gru_decoder&#39;</span><span class="p">,</span>
+        <span class="nb">input</span><span class="o">=</span><span class="n">decoder_inputs</span><span class="p">,</span>
+        <span class="n">output_mem</span><span class="o">=</span><span class="n">decoder_mem</span><span class="p">,</span>
+        <span class="n">size</span><span class="o">=</span><span class="n">decoder_size</span><span class="p">)</span>
     <span class="c1"># Defines the output function.</span>
-    <span class="n">out</span> <span class="o">=</span> <span class="n">mixed_layer</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="p">[</span><span class="n">full_matrix_projection</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">gru_step</span><span class="p">)],</span>
-                      <span class="n">size</span><span class="o">=</span><span class="n">target_dict_dim</span><span class="p">,</span>
-                      <span class="n">bias_attr</span><span class="o">=</span><span class="bp">True</span><span class="p">,</span>
-                      <span class="n">act</span><span class="o">=</span><span class="n">SoftmaxActivation</span><span class="p">())</span>
+    <span class="n">out</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">mixed</span><span class="p">(</span>
+        <span class="n">size</span><span class="o">=</span><span class="n">target_dict_dim</span><span class="p">,</span>
+        <span class="n">bias_attr</span><span class="o">=</span><span class="bp">True</span><span class="p">,</span>
+        <span class="n">act</span><span class="o">=</span><span class="n">paddle</span><span class="o">.</span><span class="n">activation</span><span class="o">.</span><span class="n">Softmax</span><span class="p">(),</span>
+        <span class="nb">input</span><span class="o">=</span><span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">full_matrix_projection</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">gru_step</span><span class="p">))</span>
     <span class="k">return</span> <span class="n">out</span>
 </pre></div>
 </div>
@@ -341,44 +351,36 @@ Its <strong>output function</strong> simply takes <span class="math">\(x_t\)</sp
 <li><code class="code docutils literal"><span class="pre">max_length</span></code>: the maximum length of the generated sentences.</li>
 </ul>
 </li>
-<li>use <code class="code docutils literal"><span class="pre">seqtext_printer_evaluator</span></code> to print text according to index matrix and dictionary. This function needs to set:<ul>
-<li><code class="code docutils literal"><span class="pre">id_input</span></code>: the integer ID of the data, used to identify the corresponding output in the generated files.</li>
-<li><code class="code docutils literal"><span class="pre">dict_file</span></code>: the dictionary file for converting word id to word.</li>
-<li><code class="code docutils literal"><span class="pre">result_file</span></code>: the path of the generation result file.</li>
-</ul>
-</li>
 </ul>
 <p>The code is listed below:</p>
-<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">group_inputs</span><span class="o">=</span><span class="p">[</span><span class="n">StaticInput</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">encoded_vector</span><span class="p">,</span><span class="n">is_seq</span><span class="o">=</span><span class="bp">True</span><span class="p">),</span>
-              <span class="n">StaticInput</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">encoded_proj</span><span class="p">,</span><span class="n">is_seq</span><span class="o">=</span><span class="bp">True</span><span class="p">)]</span>
+<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">group_input1</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">StaticInput</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">encoded_vector</span><span class="p">,</span> <span class="n">is_seq</span><span class="o">=</span><span class="bp">True</span><span class="p">)</span>
+<span class="n">group_input2</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">StaticInput</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">encoded_proj</span><span class="p">,</span> <span class="n">is_seq</span><span class="o">=</span><span class="bp">True</span><span class="p">)</span>
+<span class="n">group_inputs</span> <span class="o">=</span> <span class="p">[</span><span class="n">group_input1</span><span class="p">,</span> <span class="n">group_input2</span><span class="p">]</span>
 <span class="c1"># In generation, decoder predicts a next target word based on</span>
 <span class="c1"># the encoded source sequence and the last generated target word.</span>
 <span class="c1"># The encoded source sequence (encoder&#39;s output) must be specified by</span>
 <span class="c1"># StaticInput which is a read-only memory.</span>
 <span class="c1"># Here, GeneratedInputs automatically fetchs the last generated word,</span>
 <span class="c1"># which is initialized by a start mark, such as &lt;s&gt;.</span>
-<span class="n">trg_embedding</span> <span class="o">=</span> <span class="n">GeneratedInput</span><span class="p">(</span>
-    <span class="n">size</span><span class="o">=</span><span class="n">target_dict_dim</span><span class="p">,</span>
-    <span class="n">embedding_name</span><span class="o">=</span><span class="s1">&#39;_target_language_embedding&#39;</span><span class="p">,</span>
-    <span class="n">embedding_size</span><span class="o">=</span><span class="n">word_vector_dim</span><span class="p">)</span>
+<span class="n">trg_embedding</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">GeneratedInput</span><span class="p">(</span>
+        <span class="n">size</span><span class="o">=</span><span class="n">target_dict_dim</span><span class="p">,</span>
+        <span class="n">embedding_name</span><span class="o">=</span><span class="s1">&#39;_target_language_embedding&#39;</span><span class="p">,</span>
+        <span class="n">embedding_size</span><span class="o">=</span><span class="n">word_vector_dim</span><span class="p">)</span>
 <span class="n">group_inputs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">trg_embedding</span><span class="p">)</span>
-<span class="n">beam_gen</span> <span class="o">=</span> <span class="n">beam_search</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="n">decoder_group_name</span><span class="p">,</span>
-                       <span class="n">step</span><span class="o">=</span><span class="n">gru_decoder_with_attention</span><span class="p">,</span>
-                       <span class="nb">input</span><span class="o">=</span><span class="n">group_inputs</span><span class="p">,</span>
-                       <span class="n">bos_id</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="c1"># Beginnning token.</span>
-                       <span class="n">eos_id</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="c1"># End of sentence token.</span>
-                       <span class="n">beam_size</span><span class="o">=</span><span class="n">beam_size</span><span class="p">,</span>
-                       <span class="n">max_length</span><span class="o">=</span><span class="n">max_length</span><span class="p">)</span>
-
-<span class="n">seqtext_printer_evaluator</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">beam_gen</span><span class="p">,</span>
-                          <span class="n">id_input</span><span class="o">=</span><span class="n">data_layer</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s2">&quot;sent_id&quot;</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="mi">1</span><span class="p">),</span>
-                          <span class="n">dict_file</span><span class="o">=</span><span class="n">trg_dict_path</span><span class="p">,</span>
-                          <span class="n">result_file</span><span class="o">=</span><span class="n">gen_trans_file</span><span class="p">)</span>
-<span class="n">outputs</span><span class="p">(</span><span class="n">beam_gen</span><span class="p">)</span>
+<span class="n">beam_gen</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">beam_search</span><span class="p">(</span>
+        <span class="n">name</span><span class="o">=</span><span class="n">decoder_group_name</span><span class="p">,</span>
+        <span class="n">step</span><span class="o">=</span><span class="n">gru_decoder_with_attention</span><span class="p">,</span>
+        <span class="nb">input</span><span class="o">=</span><span class="n">group_inputs</span><span class="p">,</span>
+        <span class="n">bos_id</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="c1"># Beginnning token.</span>
+        <span class="n">eos_id</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="c1"># End of sentence token.</span>
+        <span class="n">beam_size</span><span class="o">=</span><span class="n">beam_size</span><span class="p">,</span>
+        <span class="n">max_length</span><span class="o">=</span><span class="n">max_length</span><span class="p">)</span>
+
+<span class="k">return</span> <span class="n">beam_gen</span>
 </pre></div>
 </div>
-<p>Notice that this generation technique is only useful for decoder like generation process. If you are working on sequence tagging tasks, please refer to <a class="reference internal" href="../../../tutorials/semantic_role_labeling/index_en.html#semantic-role-labeling"><span class="std std-ref">Semantic Role labeling Tutorial</span></a> for more details.</p>
-<p>The full configuration file is located at <code class="code docutils literal"><span class="pre">demo/seqToseq/seqToseq_net.py</span></code>.</p>
+<p>Notice that this generation technique is only useful for decoder like generation process. If you are working on sequence tagging tasks, please refer to <a class="reference external" href="https://github.com/PaddlePaddle/book/tree/develop/06.understand_sentiment">book/06.understand_sentiment</a> for more details.</p>
+<p>The full configuration file is located at <a class="reference external" href="https://github.com/PaddlePaddle/book/blob/develop/08.machine_translation/train.py">book/08.machine_translation/train.py</a> .</p>
 </div>
 </div>
 
@@ -387,6 +389,15 @@ Its <strong>output function</strong> simply takes <span class="math">\(x_t\)</sp
           </div>
           <footer>
   
+    <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
+      
+        <a href="../../optimization/gpu_profiling_en.html" class="btn btn-neutral float-right" title="Tune GPU Performance" accesskey="n">Next <span class="fa fa-arrow-circle-right"></span></a>
+      
+      
+        <a href="index_en.html" class="btn btn-neutral" title="RNN Models" accesskey="p"><span class="fa fa-arrow-circle-left"></span> Previous</a>
+      
+    </div>
+  
 
   <hr/>
 

develop/doc/howto/dev/contribute_to_paddle_en.html

@@ -130,7 +130,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2 current"><a class="current reference internal" href="#">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/howto/dev/new_layer_en.html

@@ -130,7 +130,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2 current"><a class="current reference internal" href="#">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/howto/index_en.html

@@ -129,7 +129,10 @@
 <li class="toctree-l2"><a class="reference internal" href="usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/howto/optimization/gpu_profiling_en.html

@@ -35,7 +35,7 @@
     <link rel="top" title="PaddlePaddle  documentation" href="../../index.html"/>
         <link rel="up" title="HOW TO" href="../index_en.html"/>
         <link rel="next" title="API" href="../../api/index_en.html"/>
-        <link rel="prev" title="RNN Models" href="../deep_model/rnn/index_en.html"/> 
+        <link rel="prev" title="RNN Configuration" href="../deep_model/rnn/rnn_config_en.html"/> 
 
   <link rel="stylesheet" href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" type="text/css" />
   <link rel="stylesheet" href="../../_static/css/override.css" type="text/css" />
@@ -130,7 +130,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2 current"><a class="current reference internal" href="#">Tune GPU Performance</a></li>
 </ul>
 </li>
@@ -515,7 +518,7 @@ Your mileage may vary!</p>
         <a href="../../api/index_en.html" class="btn btn-neutral float-right" title="API" accesskey="n">Next <span class="fa fa-arrow-circle-right"></span></a>
       
       
-        <a href="../deep_model/rnn/index_en.html" class="btn btn-neutral" title="RNN Models" accesskey="p"><span class="fa fa-arrow-circle-left"></span> Previous</a>
+        <a href="../deep_model/rnn/rnn_config_en.html" class="btn btn-neutral" title="RNN Configuration" accesskey="p"><span class="fa fa-arrow-circle-left"></span> Previous</a>
       
     </div>
   

develop/doc/howto/usage/cluster/cluster_train_en.html

@@ -130,7 +130,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/howto/usage/cmd_parameter/arguments_en.html

@@ -130,7 +130,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/howto/usage/cmd_parameter/detail_introduction_en.html

@@ -130,7 +130,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/howto/usage/cmd_parameter/index_en.html

@@ -130,7 +130,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/howto/usage/cmd_parameter/use_case_en.html

@@ -130,7 +130,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/howto/usage/k8s/k8s_aws_en.html

@@ -130,7 +130,10 @@
 <li class="toctree-l2 current"><a class="current reference internal" href="#">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/howto/usage/k8s/k8s_en.html

@@ -130,7 +130,10 @@
 <li class="toctree-l2"><a class="reference internal" href="k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/howto/usage/k8s/src/k8s_data/README.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../../dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../../dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../../../deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../../../deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../../../deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../../../optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/howto/usage/k8s/src/k8s_train/README.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../../dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../../dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../../../deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../../../deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../../../deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../../../optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/index_en.html

@@ -128,7 +128,10 @@
 <li class="toctree-l2"><a class="reference internal" href="howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/search.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/tutorials/embedding_model/index_en.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/tutorials/gan/index_en.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/tutorials/image_classification/index_en.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/tutorials/imagenet_model/resnet_model_en.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/tutorials/index_en.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/tutorials/quick_start/index_en.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/tutorials/rec/ml_dataset_en.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/tutorials/rec/ml_regression_en.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/tutorials/semantic_role_labeling/index_en.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/tutorials/sentiment_analysis/index_en.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc/tutorials/text_generation/index_en.html

@@ -127,7 +127,10 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/new_layer_en.html">Write New Layers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
-<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
+</ul>
+</li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
 </ul>
 </li>

develop/doc_cn/_sources/howto/deep_model/rnn/index_cn.rst.txt

@@ -4,6 +4,7 @@ RNN相关模型
 ..  toctree::
   :maxdepth: 1
 
+  rnn_config_cn.rst
   recurrent_group_cn.md
   hierarchical_layer_cn.rst
   hrnn_rnn_api_compare_cn.rst

develop/doc_cn/_sources/howto/deep_model/rnn/rnn_config_cn.rst.txt

@@ -5,36 +5,13 @@ RNN配置
 中配置循环神经网络（RNN）。PaddlePaddle
 高度支持灵活和高效的循环神经网络配置。 在本教程中，您将了解如何：
 
--  准备用来学习循环神经网络的序列数据。
 -  配置循环神经网络架构。
 -  使用学习完成的循环神经网络模型生成序列。
 
 我们将使用 vanilla 循环神经网络和 sequence to sequence
 模型来指导你完成这些步骤。sequence to sequence
-模型的代码可以在\ ``demo / seqToseq``\ 找到。
-
-准备序列数据
-------------
-
-PaddlePaddle
-不需要对序列数据进行任何预处理，例如填充。唯一需要做的是将相应类型设置为输入。例如，以下代码段定义了三个输入。
-它们都是序列，它们的大小是\ ``src_dict``\ ，\ ``trg_dict``\ 和\ ``trg_dict``\ ：
-
-.. code:: python
-
-    settings.input_types = [
-      integer_value_sequence(len(settings.src_dict)),
-      integer_value_sequence(len(settings.trg_dict)),
-      integer_value_sequence(len(settings.trg_dict))]
-
-在\ ``process``\ 函数中，每个\ ``yield``\ 函数将返回三个整数列表。每个整数列表被视为一个整数序列：
-
-.. code:: python
-
-    yield src_ids, trg_ids, trg_ids_next
-
-有关如何编写数据提供程序的更多细节描述，请参考 :ref:`api_pydataprovider2` 。完整的数据提供文件在
-``demo/seqToseq/dataprovider.py``\ 。
+模型的代码可以在 `book/08.machine_translation <https://github.com/PaddlePaddle/book/tree/develop/08.machine_translation>`_ 找到。
+wmt14数据的提供文件在 `python/paddle/v2/dataset/wmt14.py <https://github.com/PaddlePaddle/Paddle/blob/develop/python/paddle/v2/dataset/wmt14.py>`_ 。
 
 配置循环神经网络架构
 --------------------
@@ -85,19 +62,19 @@ vanilla
                    act=None,
                    rnn_layer_attr=None):
         def __rnn_step__(ipt):
-           out_mem = memory(name=name, size=size)
-           rnn_out = mixed_layer(input = [full_matrix_projection(ipt),
-                                          full_matrix_projection(out_mem)],
-                                 name = name,
-                                 bias_attr = rnn_bias_attr,
-                                 act = act,
-                                 layer_attr = rnn_layer_attr,
-                                 size = size)
+           out_mem = paddle.layer.memory(name=name, size=size)
+           rnn_out = paddle.layer.mixed(input = [paddle.layer.full_matrix_projection(input=ipt),
+                                                 paddle.layer.full_matrix_projection(input=out_mem)],
+                                        name = name,
+                                        bias_attr = rnn_bias_attr,
+                                        act = act,
+                                        layer_attr = rnn_layer_attr,
+                                        size = size)
            return rnn_out
-        return recurrent_group(name='%s_recurrent_group' % name,
-                               step=__rnn_step__,
-                               reverse=reverse,
-                               input=input)
+        return paddle.layer.recurrent_group(name='%s_recurrent_group' % name,
+                                            step=__rnn_step__,
+                                            reverse=reverse,
+                                            input=input)
 
 PaddlePaddle
 使用“Memory”（记忆模块）实现单步函数。\ **Memory**\ 是在PaddlePaddle中构造循环神经网络时最重要的概念。
@@ -140,43 +117,52 @@ Sequence to Sequence Model with Attention
 .. code:: python
 
     # 定义源语句的数据层
-    src_word_id = data_layer(name='source_language_word', size=source_dict_dim)
+    src_word_id = paddle.layer.data(
+        name='source_language_word',
+        type=paddle.data_type.integer_value_sequence(source_dict_dim))
     # 计算每个词的词向量
-    src_embedding = embedding_layer(
+    src_embedding = paddle.layer.embedding(
         input=src_word_id,
         size=word_vector_dim,
-        param_attr=ParamAttr(name='_source_language_embedding'))
+        param_attr=paddle.attr.ParamAttr(name='_source_language_embedding'))
     # 应用前向循环神经网络
-    src_forward = grumemory(input=src_embedding, size=encoder_size)
+    src_forward = paddle.networks.simple_gru(
+        input=src_embedding, size=encoder_size)
     # 应用反向递归神经网络（reverse=True表示反向循环神经网络）
-    src_backward = grumemory(input=src_embedding,
-                              size=encoder_size,
-                              reverse=True)
+    src_backward = paddle.networks.simple_gru(
+        input=src_embedding, size=encoder_size, reverse=True)
     # 将循环神经网络的前向和反向部分混合在一起
-    encoded_vector = concat_layer(input=[src_forward, src_backward])
+    encoded_vector = paddle.layer.concat(input=[src_forward, src_backward])
 
     # 投射编码向量到 decoder_size
-    encoder_proj = mixed_layer(input = [full_matrix_projection(encoded_vector)],
-                               size = decoder_size)
+    encoded_proj = paddle.layer.mixed(
+        size=decoder_size,
+        input=paddle.layer.full_matrix_projection(encoded_vector))
 
     # 计算反向RNN的第一个实例
-    backward_first = first_seq(input=src_backward)
+    backward_first = paddle.layer.first_seq(input=src_backward)
 
     # 投射反向RNN的第一个实例到 decoder size
-    decoder_boot = mixed_layer(input=[full_matrix_projection(backward_first)], size=decoder_size, act=TanhActivation())
+    decoder_boot = paddle.layer.mixed(
+       size=decoder_size,
+       act=paddle.activation.Tanh(),
+       input=paddle.layer.full_matrix_projection(backward_first))
 
 解码器使用 ``recurrent_group`` 来定义循环神经网络。单步函数和输出函数在
 ``gru_decoder_with_attention`` 中定义：
 
 .. code:: python
 
-    group_inputs=[StaticInput(input=encoded_vector,is_seq=True),
-                  StaticInput(input=encoded_proj,is_seq=True)]
-    trg_embedding = embedding_layer(
-        input=data_layer(name='target_language_word',
-                         size=target_dict_dim),
-        size=word_vector_dim,
-        param_attr=ParamAttr(name='_target_language_embedding'))
+    group_input1 = paddle.layer.StaticInput(input=encoded_vector, is_seq=True)
+    group_input2 = paddle.layer.StaticInput(input=encoded_proj, is_seq=True)
+    group_inputs = [group_input1, group_input2]
+    trg_embedding = paddle.layer.embedding(
+            input=paddle.layer.data(
+                name='target_language_word',
+                type=paddle.data_type.integer_value_sequence(target_dict_dim)),
+            size=word_vector_dim,
+            param_attr=paddle.attr.ParamAttr(name='_target_language_embedding'))
+        group_inputs.append(trg_embedding)
     group_inputs.append(trg_embedding)
 
     # 对于配备有注意力机制的解码器，在训练中，
@@ -185,9 +171,10 @@ Sequence to Sequence Model with Attention
     # StaticInput 意味着不同时间步的输入都是相同的值，
     # 否则它以一个序列输入，不同时间步的输入是不同的。
     # 所有输入序列应该有相同的长度。
-    decoder = recurrent_group(name=decoder_group_name,
-                              step=gru_decoder_with_attention,
-                              input=group_inputs)
+    decoder = paddle.layer.recurrent_group(
+            name=decoder_group_name,
+            step=gru_decoder_with_attention,
+            input=group_inputs)
 
 单步函数的实现如下所示。首先，它定义解码网络的\ **Memory**\ 。然后定义
 attention，门控循环单元单步函数和输出函数：
@@ -198,27 +185,32 @@ attention，门控循环单元单步函数和输出函数：
         # 定义解码器的Memory
         # Memory的输出定义在 gru_step 内
         # 注意 gru_step 应该与它的Memory名字相同
-        decoder_mem = memory(name='gru_decoder',
-                             size=decoder_size,
-                             boot_layer=decoder_boot)
+        decoder_mem = paddle.layer.memory(
+            name='gru_decoder', size=decoder_size, boot_layer=decoder_boot)
         # 计算 attention 加权编码向量
-        context = simple_attention(encoded_sequence=enc_vec,
-                                   encoded_proj=enc_proj,
-                                   decoder_state=decoder_mem)
+        context = paddle.networks.simple_attention(
+            encoded_sequence=enc_vec,
+            encoded_proj=enc_proj,
+            decoder_state=decoder_mem)
         # 混合当前词向量和attention加权编码向量
-        decoder_inputs = mixed_layer(inputs = [full_matrix_projection(context),
-                                               full_matrix_projection(current_word)],
-                                     size = decoder_size * 3)
+         decoder_inputs = paddle.layer.mixed(
+            size=decoder_size * 3,
+            input=[
+                paddle.layer.full_matrix_projection(input=context),
+                paddle.layer.full_matrix_projection(input=current_word)
+            ])
         # 定义门控循环单元循环神经网络单步函数
-        gru_step = gru_step_layer(name='gru_decoder',
-                                  input=decoder_inputs,
-                                  output_mem=decoder_mem,
-                                  size=decoder_size)
+         gru_step = paddle.layer.gru_step(
+            name='gru_decoder',
+            input=decoder_inputs,
+            output_mem=decoder_mem,
+            size=decoder_size)
         # 定义输出函数
-        out = mixed_layer(input=[full_matrix_projection(input=gru_step)],
-                          size=target_dict_dim,
-                          bias_attr=True,
-                          act=SoftmaxActivation())
+         out = paddle.layer.mixed(
+            size=target_dict_dim,
+            bias_attr=True,
+            act=paddle.activation.Softmax(),
+            input=paddle.layer.full_matrix_projection(input=gru_step))
         return out
 
 生成序列
@@ -238,41 +230,32 @@ attention，门控循环单元单步函数和输出函数：
    -  ``beam_size``: beam search 算法中的beam大小。
    -  ``max_length``: 生成序列的最大长度。
 
--  使用 ``seqtext_printer_evaluator``
-   根据索引矩阵和字典打印文本。这个函数需要设置：
-
-   -  ``id_input``: 数据的整数ID，用于标识生成的文件中的相应输出。
-   -  ``dict_file``: 用于将词ID转换为词的字典文件。
-   -  ``result_file``: 生成结果文件的路径。
-
 代码如下：
 
 .. code:: python
 
-    group_inputs=[StaticInput(input=encoded_vector,is_seq=True),
-                  StaticInput(input=encoded_proj,is_seq=True)]
+    group_input1 = paddle.layer.StaticInput(input=encoded_vector, is_seq=True)
+    group_input2 = paddle.layer.StaticInput(input=encoded_proj, is_seq=True)
+    group_inputs = [group_input1, group_input2]
     # 在生成时，解码器基于编码源序列和最后生成的目标词预测下一目标词。
     # 编码源序列（编码器输出）必须由只读Memory的 StaticInput 指定。
     # 这里， GeneratedInputs 自动获取上一个生成的词，并在最开始初始化为起始词，如 <s>。
-    trg_embedding = GeneratedInput(
-        size=target_dict_dim,
-        embedding_name='_target_language_embedding',
-        embedding_size=word_vector_dim)
+    trg_embedding = paddle.layer.GeneratedInput(
+            size=target_dict_dim,
+            embedding_name='_target_language_embedding',
+            embedding_size=word_vector_dim)
     group_inputs.append(trg_embedding)
-    beam_gen = beam_search(name=decoder_group_name,
-                           step=gru_decoder_with_attention,
-                           input=group_inputs,
-                           bos_id=0, # Beginnning token.
-                           eos_id=1, # End of sentence token.
-                           beam_size=beam_size,
-                           max_length=max_length)
-
-    seqtext_printer_evaluator(input=beam_gen,
-                              id_input=data_layer(name="sent_id", size=1),
-                              dict_file=trg_dict_path,
-                              result_file=gen_trans_file)
-    outputs(beam_gen)
-
-注意，这种生成技术只用于类似解码器的生成过程。如果你正在处理序列标记任务，请参阅 :ref:`semantic_role_labeling` 了解更多详细信息。
-
-完整的配置文件在\ ``demo/seqToseq/seqToseq_net.py``\ 。
+    beam_gen = paddle.layer.beam_search(
+            name=decoder_group_name,
+            step=gru_decoder_with_attention,
+            input=group_inputs,
+            bos_id=0, # Beginnning token.
+            eos_id=1, # End of sentence token.
+            beam_size=beam_size,
+            max_length=max_length)
+
+    return beam_gen
+
+注意，这种生成技术只用于类似解码器的生成过程。如果你正在处理序列标记任务，请参阅 `book/06.understand_sentiment <https://github.com/PaddlePaddle/book/tree/develop/06.understand_sentiment>`_ 了解更多详细信息。
+
+完整的配置文件在 `book/08.machine_translation/train.py <https://github.com/PaddlePaddle/book/blob/develop/08.machine_translation/train.py>`_ 。

develop/doc_cn/about/index_cn.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/api/index_cn.html

@@ -132,6 +132,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/api/v1/data_provider/dataprovider_cn.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/api/v1/data_provider/pydataprovider2_cn.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/api/v1/index_cn.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/api/v1/predict/swig_py_paddle_cn.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/api/v2/config/activation.html

@@ -133,6 +133,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/api/v2/config/attr.html

@@ -133,6 +133,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/api/v2/config/evaluators.html

@@ -133,6 +133,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/api/v2/config/layer.html

@@ -133,6 +133,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/api/v2/config/networks.html

@@ -133,6 +133,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/api/v2/config/optimizer.html

@@ -133,6 +133,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/api/v2/config/pooling.html

@@ -133,6 +133,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/api/v2/data.html

@@ -133,6 +133,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/api/v2/model_configs.html

@@ -133,6 +133,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/api/v2/run_logic.html

@@ -133,6 +133,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/design/api.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/design/build_system/README.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/design/cluster_train/README.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/design/cluster_train/checkpointing.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/design/cluster_train/data_dispatch.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/design/cluster_train/master_server.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/design/cluster_train/pserver_client.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/design/cluster_train/remote_parameter_updater.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/design/cluster_train/submit-job.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/design/file_manager/README.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/design/file_manager/pfs/pfsclient.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/design/multi_language_interface/00.why_plain_c.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/design/multi_language_interface/01.inference_implementation.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/design/parameters_in_cpp.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/design/reader/README.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/design/releasing_process.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/faq/index_cn.html

@@ -131,6 +131,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/genindex.html

@@ -131,6 +131,7 @@
 <li class="toctree-l2"><a class="reference internal" href="howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/getstarted/basic_usage/index_cn.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/getstarted/build_and_install/cmake/build_from_source_cn.html

@@ -133,6 +133,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/getstarted/build_and_install/docker_install_cn.html

@@ -133,6 +133,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/getstarted/build_and_install/index_cn.html

@@ -133,6 +133,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/getstarted/build_and_install/ubuntu_install_cn.html

@@ -133,6 +133,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/getstarted/concepts/use_concepts_cn.html

@@ -133,6 +133,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/getstarted/index_cn.html

@@ -132,6 +132,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/howto/cross_compiling/cross_compiling_for_android_cn.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/howto/cross_compiling/cross_compiling_for_raspberry_cn.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/howto/deep_model/rnn/hierarchical_layer_cn.html

@@ -133,6 +133,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2 current"><a class="reference internal" href="index_cn.html">RNN相关模型</a><ul class="current">
+<li class="toctree-l3"><a class="reference internal" href="rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3 current"><a class="current reference internal" href="#">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html

@@ -133,6 +133,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2 current"><a class="reference internal" href="index_cn.html">RNN相关模型</a><ul class="current">
+<li class="toctree-l3"><a class="reference internal" href="rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3 current"><a class="current reference internal" href="#">单双层RNN API对比介绍</a></li>

develop/doc_cn/howto/deep_model/rnn/index_cn.html

@@ -34,7 +34,7 @@
         <link rel="search" title="搜索" href="../../../search.html"/>
     <link rel="top" title="PaddlePaddle  文档" href="../../../index.html"/>
         <link rel="up" title="进阶指南" href="../../index_cn.html"/>
-        <link rel="next" title="Recurrent Group教程" href="recurrent_group_cn.html"/>
+        <link rel="next" title="RNN配置" href="rnn_config_cn.html"/>
         <link rel="prev" title="如何贡献代码" href="../../dev/contribute_to_paddle_cn.html"/> 
 
   <link rel="stylesheet" href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" type="text/css" />
@@ -133,6 +133,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2 current"><a class="current reference internal" href="#">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>
@@ -192,6 +193,7 @@
 <h1>RNN相关模型<a class="headerlink" href="#rnn" title="永久链接至标题">¶</a></h1>
 <div class="toctree-wrapper compound">
 <ul>
+<li class="toctree-l1"><a class="reference internal" href="rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l1"><a class="reference internal" href="recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l1"><a class="reference internal" href="hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l1"><a class="reference internal" href="hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>
@@ -206,7 +208,7 @@
   
     <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
       
-        <a href="recurrent_group_cn.html" class="btn btn-neutral float-right" title="Recurrent Group教程" accesskey="n">Next <span class="fa fa-arrow-circle-right"></span></a>
+        <a href="rnn_config_cn.html" class="btn btn-neutral float-right" title="RNN配置" accesskey="n">Next <span class="fa fa-arrow-circle-right"></span></a>
       
       
         <a href="../../dev/contribute_to_paddle_cn.html" class="btn btn-neutral" title="如何贡献代码" accesskey="p"><span class="fa fa-arrow-circle-left"></span> Previous</a>

develop/doc_cn/howto/deep_model/rnn/recurrent_group_cn.html

@@ -35,7 +35,7 @@
     <link rel="top" title="PaddlePaddle  文档" href="../../../index.html"/>
         <link rel="up" title="RNN相关模型" href="index_cn.html"/>
         <link rel="next" title="支持双层序列作为输入的Layer" href="hierarchical_layer_cn.html"/>
-        <link rel="prev" title="RNN相关模型" href="index_cn.html"/> 
+        <link rel="prev" title="RNN配置" href="rnn_config_cn.html"/> 
 
   <link rel="stylesheet" href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" type="text/css" />
   <link rel="stylesheet" href="../../../_static/css/override.css" type="text/css" />
@@ -133,6 +133,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2 current"><a class="reference internal" href="index_cn.html">RNN相关模型</a><ul class="current">
+<li class="toctree-l3"><a class="reference internal" href="rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3 current"><a class="current reference internal" href="#">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>
@@ -300,7 +301,7 @@
         <a href="hierarchical_layer_cn.html" class="btn btn-neutral float-right" title="支持双层序列作为输入的Layer" accesskey="n">Next <span class="fa fa-arrow-circle-right"></span></a>
       
       
-        <a href="index_cn.html" class="btn btn-neutral" title="RNN相关模型" accesskey="p"><span class="fa fa-arrow-circle-left"></span> Previous</a>
+        <a href="rnn_config_cn.html" class="btn btn-neutral" title="RNN配置" accesskey="p"><span class="fa fa-arrow-circle-left"></span> Previous</a>
       
     </div>
   

develop/doc_cn/howto/deep_model/rnn/rnn_config_cn.html

@@ -32,7 +32,10 @@
         <link rel="index" title="索引"
               href="../../../genindex.html"/>
         <link rel="search" title="搜索" href="../../../search.html"/>
-    <link rel="top" title="PaddlePaddle  文档" href="../../../index.html"/> 
+    <link rel="top" title="PaddlePaddle  文档" href="../../../index.html"/>
+        <link rel="up" title="RNN相关模型" href="index_cn.html"/>
+        <link rel="next" title="Recurrent Group教程" href="recurrent_group_cn.html"/>
+        <link rel="prev" title="RNN相关模型" href="index_cn.html"/> 
 
   <link rel="stylesheet" href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" type="text/css" />
   <link rel="stylesheet" href="../../../_static/css/override.css" type="text/css" />
@@ -80,9 +83,9 @@
       </div>
       <div class="doc-module">
         
-        <ul>
+        <ul class="current">
 <li class="toctree-l1"><a class="reference internal" href="../../../getstarted/index_cn.html">新手入门</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../../index_cn.html">进阶指南</a></li>
+<li class="toctree-l1 current"><a class="reference internal" href="../../index_cn.html">进阶指南</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../api/index_cn.html">API</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../faq/index_cn.html">FAQ</a></li>
 </ul>
@@ -105,7 +108,7 @@
     <nav class="doc-menu-vertical" role="navigation">
         
           
-          <ul>
+          <ul class="current">
 <li class="toctree-l1"><a class="reference internal" href="../../../getstarted/index_cn.html">新手入门</a><ul>
 <li class="toctree-l2"><a class="reference internal" href="../../../getstarted/build_and_install/index_cn.html">安装与编译</a><ul>
 <li class="toctree-l3"><a class="reference internal" href="../../../getstarted/build_and_install/docker_install_cn.html">PaddlePaddle的Docker容器使用方式</a></li>
@@ -116,7 +119,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../../getstarted/concepts/use_concepts_cn.html">基本使用概念</a></li>
 </ul>
 </li>
-<li class="toctree-l1"><a class="reference internal" href="../../index_cn.html">进阶指南</a><ul>
+<li class="toctree-l1 current"><a class="reference internal" href="../../index_cn.html">进阶指南</a><ul class="current">
 <li class="toctree-l2"><a class="reference internal" href="../../usage/cmd_parameter/index_cn.html">设置命令行参数</a><ul>
 <li class="toctree-l3"><a class="reference internal" href="../../usage/cmd_parameter/use_case_cn.html">使用案例</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../usage/cmd_parameter/arguments_cn.html">参数概述</a></li>
@@ -129,7 +132,8 @@
 <li class="toctree-l2"><a class="reference internal" href="../../usage/k8s/k8s_distributed_cn.html">Kubernetes分布式训练</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
-<li class="toctree-l2"><a class="reference internal" href="index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l2 current"><a class="reference internal" href="index_cn.html">RNN相关模型</a><ul class="current">
+<li class="toctree-l3 current"><a class="current reference internal" href="#">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>
@@ -174,6 +178,10 @@
 <div role="navigation" aria-label="breadcrumbs navigation">
   <ul class="wy-breadcrumbs">
       
+        <li><a href="../../index_cn.html">进阶指南</a> > </li>
+      
+        <li><a href="index_cn.html">RNN相关模型</a> > </li>
+      
     <li>RNN配置</li>
   </ul>
 </div>
@@ -189,33 +197,15 @@
 中配置循环神经网络（RNN）。PaddlePaddle
 高度支持灵活和高效的循环神经网络配置。 在本教程中，您将了解如何：</p>
 <ul class="simple">
-<li>准备用来学习循环神经网络的序列数据。</li>
 <li>配置循环神经网络架构。</li>
 <li>使用学习完成的循环神经网络模型生成序列。</li>
 </ul>
 <p>我们将使用 vanilla 循环神经网络和 sequence to sequence
 模型来指导你完成这些步骤。sequence to sequence
-模型的代码可以在<code class="docutils literal"><span class="pre">demo</span> <span class="pre">/</span> <span class="pre">seqToseq</span></code>找到。</p>
+模型的代码可以在 <a class="reference external" href="https://github.com/PaddlePaddle/book/tree/develop/08.machine_translation">book/08.machine_translation</a> 找到。
+wmt14数据的提供文件在 <a class="reference external" href="https://github.com/PaddlePaddle/Paddle/blob/develop/python/paddle/v2/dataset/wmt14.py">python/paddle/v2/dataset/wmt14.py</a> 。</p>
 <div class="section" id="id1">
-<h2>准备序列数据<a class="headerlink" href="#id1" title="永久链接至标题">¶</a></h2>
-<p>PaddlePaddle
-不需要对序列数据进行任何预处理，例如填充。唯一需要做的是将相应类型设置为输入。例如，以下代码段定义了三个输入。
-它们都是序列，它们的大小是<code class="docutils literal"><span class="pre">src_dict</span></code>，<code class="docutils literal"><span class="pre">trg_dict</span></code>和<code class="docutils literal"><span class="pre">trg_dict</span></code>：</p>
-<div class="code python highlight-default"><div class="highlight"><pre><span></span><span class="n">settings</span><span class="o">.</span><span class="n">input_types</span> <span class="o">=</span> <span class="p">[</span>
-  <span class="n">integer_value_sequence</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">settings</span><span class="o">.</span><span class="n">src_dict</span><span class="p">)),</span>
-  <span class="n">integer_value_sequence</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">settings</span><span class="o">.</span><span class="n">trg_dict</span><span class="p">)),</span>
-  <span class="n">integer_value_sequence</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">settings</span><span class="o">.</span><span class="n">trg_dict</span><span class="p">))]</span>
-</pre></div>
-</div>
-<p>在<code class="docutils literal"><span class="pre">process</span></code>函数中，每个<code class="docutils literal"><span class="pre">yield</span></code>函数将返回三个整数列表。每个整数列表被视为一个整数序列：</p>
-<div class="code python highlight-default"><div class="highlight"><pre><span></span><span class="k">yield</span> <span class="n">src_ids</span><span class="p">,</span> <span class="n">trg_ids</span><span class="p">,</span> <span class="n">trg_ids_next</span>
-</pre></div>
-</div>
-<p>有关如何编写数据提供程序的更多细节描述，请参考 <a class="reference internal" href="../../../api/v1/data_provider/pydataprovider2_cn.html#api-pydataprovider2"><span class="std std-ref">PyDataProvider2的使用</span></a> 。完整的数据提供文件在
-<code class="docutils literal"><span class="pre">demo/seqToseq/dataprovider.py</span></code>。</p>
-</div>
-<div class="section" id="id2">
-<h2>配置循环神经网络架构<a class="headerlink" href="#id2" title="永久链接至标题">¶</a></h2>
+<h2>配置循环神经网络架构<a class="headerlink" href="#id1" title="永久链接至标题">¶</a></h2>
 <div class="section" id="gated-recurrent-neural-network">
 <h3>简单门控循环神经网络(Gated Recurrent Neural Network)<a class="headerlink" href="#gated-recurrent-neural-network" title="永久链接至标题">¶</a></h3>
 <p>循环神经网络在每个时间步骤顺序地处理序列。下面列出了 LSTM 的架构的示例。</p>
@@ -247,19 +237,19 @@ vanilla
                <span class="n">act</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
                <span class="n">rnn_layer_attr</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
     <span class="k">def</span> <span class="nf">__rnn_step__</span><span class="p">(</span><span class="n">ipt</span><span class="p">):</span>
-       <span class="n">out_mem</span> <span class="o">=</span> <span class="n">memory</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="n">name</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="n">size</span><span class="p">)</span>
-       <span class="n">rnn_out</span> <span class="o">=</span> <span class="n">mixed_layer</span><span class="p">(</span><span class="nb">input</span> <span class="o">=</span> <span class="p">[</span><span class="n">full_matrix_projection</span><span class="p">(</span><span class="n">ipt</span><span class="p">),</span>
-                                      <span class="n">full_matrix_projection</span><span class="p">(</span><span class="n">out_mem</span><span class="p">)],</span>
-                             <span class="n">name</span> <span class="o">=</span> <span class="n">name</span><span class="p">,</span>
-                             <span class="n">bias_attr</span> <span class="o">=</span> <span class="n">rnn_bias_attr</span><span class="p">,</span>
-                             <span class="n">act</span> <span class="o">=</span> <span class="n">act</span><span class="p">,</span>
-                             <span class="n">layer_attr</span> <span class="o">=</span> <span class="n">rnn_layer_attr</span><span class="p">,</span>
-                             <span class="n">size</span> <span class="o">=</span> <span class="n">size</span><span class="p">)</span>
+       <span class="n">out_mem</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">memory</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="n">name</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="n">size</span><span class="p">)</span>
+       <span class="n">rnn_out</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">mixed</span><span class="p">(</span><span class="nb">input</span> <span class="o">=</span> <span class="p">[</span><span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">full_matrix_projection</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">ipt</span><span class="p">),</span>
+                                             <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">full_matrix_projection</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">out_mem</span><span class="p">)],</span>
+                                    <span class="n">name</span> <span class="o">=</span> <span class="n">name</span><span class="p">,</span>
+                                    <span class="n">bias_attr</span> <span class="o">=</span> <span class="n">rnn_bias_attr</span><span class="p">,</span>
+                                    <span class="n">act</span> <span class="o">=</span> <span class="n">act</span><span class="p">,</span>
+                                    <span class="n">layer_attr</span> <span class="o">=</span> <span class="n">rnn_layer_attr</span><span class="p">,</span>
+                                    <span class="n">size</span> <span class="o">=</span> <span class="n">size</span><span class="p">)</span>
        <span class="k">return</span> <span class="n">rnn_out</span>
-    <span class="k">return</span> <span class="n">recurrent_group</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;</span><span class="si">%s</span><span class="s1">_recurrent_group&#39;</span> <span class="o">%</span> <span class="n">name</span><span class="p">,</span>
-                           <span class="n">step</span><span class="o">=</span><span class="n">__rnn_step__</span><span class="p">,</span>
-                           <span class="n">reverse</span><span class="o">=</span><span class="n">reverse</span><span class="p">,</span>
-                           <span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">)</span>
+    <span class="k">return</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">recurrent_group</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;</span><span class="si">%s</span><span class="s1">_recurrent_group&#39;</span> <span class="o">%</span> <span class="n">name</span><span class="p">,</span>
+                                        <span class="n">step</span><span class="o">=</span><span class="n">__rnn_step__</span><span class="p">,</span>
+                                        <span class="n">reverse</span><span class="o">=</span><span class="n">reverse</span><span class="p">,</span>
+                                        <span class="nb">input</span><span class="o">=</span><span class="nb">input</span><span class="p">)</span>
 </pre></div>
 </div>
 <p>PaddlePaddle
@@ -292,41 +282,50 @@ layer(引导层)</strong>，其输出被用作Memory的初始值。
 维空间。这通过获得反向循环网络的第一个实例，并将其投射到
 <code class="docutils literal"><span class="pre">decoder_size</span></code> 维空间完成：</p>
 <div class="code python highlight-default"><div class="highlight"><pre><span></span><span class="c1"># 定义源语句的数据层</span>
-<span class="n">src_word_id</span> <span class="o">=</span> <span class="n">data_layer</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;source_language_word&#39;</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="n">source_dict_dim</span><span class="p">)</span>
+<span class="n">src_word_id</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">data</span><span class="p">(</span>
+    <span class="n">name</span><span class="o">=</span><span class="s1">&#39;source_language_word&#39;</span><span class="p">,</span>
+    <span class="nb">type</span><span class="o">=</span><span class="n">paddle</span><span class="o">.</span><span class="n">data_type</span><span class="o">.</span><span class="n">integer_value_sequence</span><span class="p">(</span><span class="n">source_dict_dim</span><span class="p">))</span>
 <span class="c1"># 计算每个词的词向量</span>
-<span class="n">src_embedding</span> <span class="o">=</span> <span class="n">embedding_layer</span><span class="p">(</span>
+<span class="n">src_embedding</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">embedding</span><span class="p">(</span>
     <span class="nb">input</span><span class="o">=</span><span class="n">src_word_id</span><span class="p">,</span>
     <span class="n">size</span><span class="o">=</span><span class="n">word_vector_dim</span><span class="p">,</span>
-    <span class="n">param_attr</span><span class="o">=</span><span class="n">ParamAttr</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;_source_language_embedding&#39;</span><span class="p">))</span>
+    <span class="n">param_attr</span><span class="o">=</span><span class="n">paddle</span><span class="o">.</span><span class="n">attr</span><span class="o">.</span><span class="n">ParamAttr</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;_source_language_embedding&#39;</span><span class="p">))</span>
 <span class="c1"># 应用前向循环神经网络</span>
-<span class="n">src_forward</span> <span class="o">=</span> <span class="n">grumemory</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">src_embedding</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="n">encoder_size</span><span class="p">)</span>
+<span class="n">src_forward</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">networks</span><span class="o">.</span><span class="n">simple_gru</span><span class="p">(</span>
+    <span class="nb">input</span><span class="o">=</span><span class="n">src_embedding</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="n">encoder_size</span><span class="p">)</span>
 <span class="c1"># 应用反向递归神经网络（reverse=True表示反向循环神经网络）</span>
-<span class="n">src_backward</span> <span class="o">=</span> <span class="n">grumemory</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">src_embedding</span><span class="p">,</span>
-                          <span class="n">size</span><span class="o">=</span><span class="n">encoder_size</span><span class="p">,</span>
-                          <span class="n">reverse</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
+<span class="n">src_backward</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">networks</span><span class="o">.</span><span class="n">simple_gru</span><span class="p">(</span>
+    <span class="nb">input</span><span class="o">=</span><span class="n">src_embedding</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="n">encoder_size</span><span class="p">,</span> <span class="n">reverse</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
 <span class="c1"># 将循环神经网络的前向和反向部分混合在一起</span>
-<span class="n">encoded_vector</span> <span class="o">=</span> <span class="n">concat_layer</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="p">[</span><span class="n">src_forward</span><span class="p">,</span> <span class="n">src_backward</span><span class="p">])</span>
+<span class="n">encoded_vector</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">concat</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="p">[</span><span class="n">src_forward</span><span class="p">,</span> <span class="n">src_backward</span><span class="p">])</span>
 
 <span class="c1"># 投射编码向量到 decoder_size</span>
-<span class="n">encoder_proj</span> <span class="o">=</span> <span class="n">mixed_layer</span><span class="p">(</span><span class="nb">input</span> <span class="o">=</span> <span class="p">[</span><span class="n">full_matrix_projection</span><span class="p">(</span><span class="n">encoded_vector</span><span class="p">)],</span>
-                           <span class="n">size</span> <span class="o">=</span> <span class="n">decoder_size</span><span class="p">)</span>
+<span class="n">encoded_proj</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">mixed</span><span class="p">(</span>
+    <span class="n">size</span><span class="o">=</span><span class="n">decoder_size</span><span class="p">,</span>
+    <span class="nb">input</span><span class="o">=</span><span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">full_matrix_projection</span><span class="p">(</span><span class="n">encoded_vector</span><span class="p">))</span>
 
 <span class="c1"># 计算反向RNN的第一个实例</span>
-<span class="n">backward_first</span> <span class="o">=</span> <span class="n">first_seq</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">src_backward</span><span class="p">)</span>
+<span class="n">backward_first</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">first_seq</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">src_backward</span><span class="p">)</span>
 
 <span class="c1"># 投射反向RNN的第一个实例到 decoder size</span>
-<span class="n">decoder_boot</span> <span class="o">=</span> <span class="n">mixed_layer</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="p">[</span><span class="n">full_matrix_projection</span><span class="p">(</span><span class="n">backward_first</span><span class="p">)],</span> <span class="n">size</span><span class="o">=</span><span class="n">decoder_size</span><span class="p">,</span> <span class="n">act</span><span class="o">=</span><span class="n">TanhActivation</span><span class="p">())</span>
+<span class="n">decoder_boot</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">mixed</span><span class="p">(</span>
+   <span class="n">size</span><span class="o">=</span><span class="n">decoder_size</span><span class="p">,</span>
+   <span class="n">act</span><span class="o">=</span><span class="n">paddle</span><span class="o">.</span><span class="n">activation</span><span class="o">.</span><span class="n">Tanh</span><span class="p">(),</span>
+   <span class="nb">input</span><span class="o">=</span><span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">full_matrix_projection</span><span class="p">(</span><span class="n">backward_first</span><span class="p">))</span>
 </pre></div>
 </div>
 <p>解码器使用 <code class="docutils literal"><span class="pre">recurrent_group</span></code> 来定义循环神经网络。单步函数和输出函数在
 <code class="docutils literal"><span class="pre">gru_decoder_with_attention</span></code> 中定义：</p>
-<div class="code python highlight-default"><div class="highlight"><pre><span></span><span class="n">group_inputs</span><span class="o">=</span><span class="p">[</span><span class="n">StaticInput</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">encoded_vector</span><span class="p">,</span><span class="n">is_seq</span><span class="o">=</span><span class="kc">True</span><span class="p">),</span>
-              <span class="n">StaticInput</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">encoded_proj</span><span class="p">,</span><span class="n">is_seq</span><span class="o">=</span><span class="kc">True</span><span class="p">)]</span>
-<span class="n">trg_embedding</span> <span class="o">=</span> <span class="n">embedding_layer</span><span class="p">(</span>
-    <span class="nb">input</span><span class="o">=</span><span class="n">data_layer</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;target_language_word&#39;</span><span class="p">,</span>
-                     <span class="n">size</span><span class="o">=</span><span class="n">target_dict_dim</span><span class="p">),</span>
-    <span class="n">size</span><span class="o">=</span><span class="n">word_vector_dim</span><span class="p">,</span>
-    <span class="n">param_attr</span><span class="o">=</span><span class="n">ParamAttr</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;_target_language_embedding&#39;</span><span class="p">))</span>
+<div class="code python highlight-default"><div class="highlight"><pre><span></span><span class="n">group_input1</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">StaticInput</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">encoded_vector</span><span class="p">,</span> <span class="n">is_seq</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
+<span class="n">group_input2</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">StaticInput</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">encoded_proj</span><span class="p">,</span> <span class="n">is_seq</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
+<span class="n">group_inputs</span> <span class="o">=</span> <span class="p">[</span><span class="n">group_input1</span><span class="p">,</span> <span class="n">group_input2</span><span class="p">]</span>
+<span class="n">trg_embedding</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">embedding</span><span class="p">(</span>
+        <span class="nb">input</span><span class="o">=</span><span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">data</span><span class="p">(</span>
+            <span class="n">name</span><span class="o">=</span><span class="s1">&#39;target_language_word&#39;</span><span class="p">,</span>
+            <span class="nb">type</span><span class="o">=</span><span class="n">paddle</span><span class="o">.</span><span class="n">data_type</span><span class="o">.</span><span class="n">integer_value_sequence</span><span class="p">(</span><span class="n">target_dict_dim</span><span class="p">)),</span>
+        <span class="n">size</span><span class="o">=</span><span class="n">word_vector_dim</span><span class="p">,</span>
+        <span class="n">param_attr</span><span class="o">=</span><span class="n">paddle</span><span class="o">.</span><span class="n">attr</span><span class="o">.</span><span class="n">ParamAttr</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;_target_language_embedding&#39;</span><span class="p">))</span>
+    <span class="n">group_inputs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">trg_embedding</span><span class="p">)</span>
 <span class="n">group_inputs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">trg_embedding</span><span class="p">)</span>
 
 <span class="c1"># 对于配备有注意力机制的解码器，在训练中，</span>
@@ -335,9 +334,10 @@ layer(引导层)</strong>，其输出被用作Memory的初始值。
 <span class="c1"># StaticInput 意味着不同时间步的输入都是相同的值，</span>
 <span class="c1"># 否则它以一个序列输入，不同时间步的输入是不同的。</span>
 <span class="c1"># 所有输入序列应该有相同的长度。</span>
-<span class="n">decoder</span> <span class="o">=</span> <span class="n">recurrent_group</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="n">decoder_group_name</span><span class="p">,</span>
-                          <span class="n">step</span><span class="o">=</span><span class="n">gru_decoder_with_attention</span><span class="p">,</span>
-                          <span class="nb">input</span><span class="o">=</span><span class="n">group_inputs</span><span class="p">)</span>
+<span class="n">decoder</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">recurrent_group</span><span class="p">(</span>
+        <span class="n">name</span><span class="o">=</span><span class="n">decoder_group_name</span><span class="p">,</span>
+        <span class="n">step</span><span class="o">=</span><span class="n">gru_decoder_with_attention</span><span class="p">,</span>
+        <span class="nb">input</span><span class="o">=</span><span class="n">group_inputs</span><span class="p">)</span>
 </pre></div>
 </div>
 <p>单步函数的实现如下所示。首先，它定义解码网络的<strong>Memory</strong>。然后定义
@@ -346,34 +346,39 @@ attention，门控循环单元单步函数和输出函数：</p>
     <span class="c1"># 定义解码器的Memory</span>
     <span class="c1"># Memory的输出定义在 gru_step 内</span>
     <span class="c1"># 注意 gru_step 应该与它的Memory名字相同</span>
-    <span class="n">decoder_mem</span> <span class="o">=</span> <span class="n">memory</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;gru_decoder&#39;</span><span class="p">,</span>
-                         <span class="n">size</span><span class="o">=</span><span class="n">decoder_size</span><span class="p">,</span>
-                         <span class="n">boot_layer</span><span class="o">=</span><span class="n">decoder_boot</span><span class="p">)</span>
+    <span class="n">decoder_mem</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">memory</span><span class="p">(</span>
+        <span class="n">name</span><span class="o">=</span><span class="s1">&#39;gru_decoder&#39;</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="n">decoder_size</span><span class="p">,</span> <span class="n">boot_layer</span><span class="o">=</span><span class="n">decoder_boot</span><span class="p">)</span>
     <span class="c1"># 计算 attention 加权编码向量</span>
-    <span class="n">context</span> <span class="o">=</span> <span class="n">simple_attention</span><span class="p">(</span><span class="n">encoded_sequence</span><span class="o">=</span><span class="n">enc_vec</span><span class="p">,</span>
-                               <span class="n">encoded_proj</span><span class="o">=</span><span class="n">enc_proj</span><span class="p">,</span>
-                               <span class="n">decoder_state</span><span class="o">=</span><span class="n">decoder_mem</span><span class="p">)</span>
+    <span class="n">context</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">networks</span><span class="o">.</span><span class="n">simple_attention</span><span class="p">(</span>
+        <span class="n">encoded_sequence</span><span class="o">=</span><span class="n">enc_vec</span><span class="p">,</span>
+        <span class="n">encoded_proj</span><span class="o">=</span><span class="n">enc_proj</span><span class="p">,</span>
+        <span class="n">decoder_state</span><span class="o">=</span><span class="n">decoder_mem</span><span class="p">)</span>
     <span class="c1"># 混合当前词向量和attention加权编码向量</span>
-    <span class="n">decoder_inputs</span> <span class="o">=</span> <span class="n">mixed_layer</span><span class="p">(</span><span class="n">inputs</span> <span class="o">=</span> <span class="p">[</span><span class="n">full_matrix_projection</span><span class="p">(</span><span class="n">context</span><span class="p">),</span>
-                                           <span class="n">full_matrix_projection</span><span class="p">(</span><span class="n">current_word</span><span class="p">)],</span>
-                                 <span class="n">size</span> <span class="o">=</span> <span class="n">decoder_size</span> <span class="o">*</span> <span class="mi">3</span><span class="p">)</span>
+     <span class="n">decoder_inputs</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">mixed</span><span class="p">(</span>
+        <span class="n">size</span><span class="o">=</span><span class="n">decoder_size</span> <span class="o">*</span> <span class="mi">3</span><span class="p">,</span>
+        <span class="nb">input</span><span class="o">=</span><span class="p">[</span>
+            <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">full_matrix_projection</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">context</span><span class="p">),</span>
+            <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">full_matrix_projection</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">current_word</span><span class="p">)</span>
+        <span class="p">])</span>
     <span class="c1"># 定义门控循环单元循环神经网络单步函数</span>
-    <span class="n">gru_step</span> <span class="o">=</span> <span class="n">gru_step_layer</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;gru_decoder&#39;</span><span class="p">,</span>
-                              <span class="nb">input</span><span class="o">=</span><span class="n">decoder_inputs</span><span class="p">,</span>
-                              <span class="n">output_mem</span><span class="o">=</span><span class="n">decoder_mem</span><span class="p">,</span>
-                              <span class="n">size</span><span class="o">=</span><span class="n">decoder_size</span><span class="p">)</span>
+     <span class="n">gru_step</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">gru_step</span><span class="p">(</span>
+        <span class="n">name</span><span class="o">=</span><span class="s1">&#39;gru_decoder&#39;</span><span class="p">,</span>
+        <span class="nb">input</span><span class="o">=</span><span class="n">decoder_inputs</span><span class="p">,</span>
+        <span class="n">output_mem</span><span class="o">=</span><span class="n">decoder_mem</span><span class="p">,</span>
+        <span class="n">size</span><span class="o">=</span><span class="n">decoder_size</span><span class="p">)</span>
     <span class="c1"># 定义输出函数</span>
-    <span class="n">out</span> <span class="o">=</span> <span class="n">mixed_layer</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="p">[</span><span class="n">full_matrix_projection</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">gru_step</span><span class="p">)],</span>
-                      <span class="n">size</span><span class="o">=</span><span class="n">target_dict_dim</span><span class="p">,</span>
-                      <span class="n">bias_attr</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
-                      <span class="n">act</span><span class="o">=</span><span class="n">SoftmaxActivation</span><span class="p">())</span>
+     <span class="n">out</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">mixed</span><span class="p">(</span>
+        <span class="n">size</span><span class="o">=</span><span class="n">target_dict_dim</span><span class="p">,</span>
+        <span class="n">bias_attr</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
+        <span class="n">act</span><span class="o">=</span><span class="n">paddle</span><span class="o">.</span><span class="n">activation</span><span class="o">.</span><span class="n">Softmax</span><span class="p">(),</span>
+        <span class="nb">input</span><span class="o">=</span><span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">full_matrix_projection</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">gru_step</span><span class="p">))</span>
     <span class="k">return</span> <span class="n">out</span>
 </pre></div>
 </div>
 </div>
 </div>
-<div class="section" id="id3">
-<h2>生成序列<a class="headerlink" href="#id3" title="永久链接至标题">¶</a></h2>
+<div class="section" id="id2">
+<h2>生成序列<a class="headerlink" href="#id2" title="永久链接至标题">¶</a></h2>
 <p>训练模型后，我们可以使用它来生成序列。通常的做法是使用<strong>beam search</strong>
 生成序列。以下代码片段定义 beam search 算法。注意，<code class="docutils literal"><span class="pre">beam_search</span></code>
 函数假设 <code class="docutils literal"><span class="pre">step</span></code> 的输出函数返回的是下一个时刻输出词的 softmax
@@ -388,42 +393,33 @@ attention，门控循环单元单步函数和输出函数：</p>
 <li><code class="docutils literal"><span class="pre">max_length</span></code>: 生成序列的最大长度。</li>
 </ul>
 </li>
-<li>使用 <code class="docutils literal"><span class="pre">seqtext_printer_evaluator</span></code>
-根据索引矩阵和字典打印文本。这个函数需要设置：<ul>
-<li><code class="docutils literal"><span class="pre">id_input</span></code>: 数据的整数ID，用于标识生成的文件中的相应输出。</li>
-<li><code class="docutils literal"><span class="pre">dict_file</span></code>: 用于将词ID转换为词的字典文件。</li>
-<li><code class="docutils literal"><span class="pre">result_file</span></code>: 生成结果文件的路径。</li>
-</ul>
-</li>
 </ul>
 <p>代码如下：</p>
-<div class="code python highlight-default"><div class="highlight"><pre><span></span><span class="n">group_inputs</span><span class="o">=</span><span class="p">[</span><span class="n">StaticInput</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">encoded_vector</span><span class="p">,</span><span class="n">is_seq</span><span class="o">=</span><span class="kc">True</span><span class="p">),</span>
-              <span class="n">StaticInput</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">encoded_proj</span><span class="p">,</span><span class="n">is_seq</span><span class="o">=</span><span class="kc">True</span><span class="p">)]</span>
+<div class="code python highlight-default"><div class="highlight"><pre><span></span><span class="n">group_input1</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">StaticInput</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">encoded_vector</span><span class="p">,</span> <span class="n">is_seq</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
+<span class="n">group_input2</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">StaticInput</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">encoded_proj</span><span class="p">,</span> <span class="n">is_seq</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
+<span class="n">group_inputs</span> <span class="o">=</span> <span class="p">[</span><span class="n">group_input1</span><span class="p">,</span> <span class="n">group_input2</span><span class="p">]</span>
 <span class="c1"># 在生成时，解码器基于编码源序列和最后生成的目标词预测下一目标词。</span>
 <span class="c1"># 编码源序列（编码器输出）必须由只读Memory的 StaticInput 指定。</span>
 <span class="c1"># 这里， GeneratedInputs 自动获取上一个生成的词，并在最开始初始化为起始词，如 &lt;s&gt;。</span>
-<span class="n">trg_embedding</span> <span class="o">=</span> <span class="n">GeneratedInput</span><span class="p">(</span>
-    <span class="n">size</span><span class="o">=</span><span class="n">target_dict_dim</span><span class="p">,</span>
-    <span class="n">embedding_name</span><span class="o">=</span><span class="s1">&#39;_target_language_embedding&#39;</span><span class="p">,</span>
-    <span class="n">embedding_size</span><span class="o">=</span><span class="n">word_vector_dim</span><span class="p">)</span>
+<span class="n">trg_embedding</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">GeneratedInput</span><span class="p">(</span>
+        <span class="n">size</span><span class="o">=</span><span class="n">target_dict_dim</span><span class="p">,</span>
+        <span class="n">embedding_name</span><span class="o">=</span><span class="s1">&#39;_target_language_embedding&#39;</span><span class="p">,</span>
+        <span class="n">embedding_size</span><span class="o">=</span><span class="n">word_vector_dim</span><span class="p">)</span>
 <span class="n">group_inputs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">trg_embedding</span><span class="p">)</span>
-<span class="n">beam_gen</span> <span class="o">=</span> <span class="n">beam_search</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="n">decoder_group_name</span><span class="p">,</span>
-                       <span class="n">step</span><span class="o">=</span><span class="n">gru_decoder_with_attention</span><span class="p">,</span>
-                       <span class="nb">input</span><span class="o">=</span><span class="n">group_inputs</span><span class="p">,</span>
-                       <span class="n">bos_id</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="c1"># Beginnning token.</span>
-                       <span class="n">eos_id</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="c1"># End of sentence token.</span>
-                       <span class="n">beam_size</span><span class="o">=</span><span class="n">beam_size</span><span class="p">,</span>
-                       <span class="n">max_length</span><span class="o">=</span><span class="n">max_length</span><span class="p">)</span>
-
-<span class="n">seqtext_printer_evaluator</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">beam_gen</span><span class="p">,</span>
-                          <span class="n">id_input</span><span class="o">=</span><span class="n">data_layer</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s2">&quot;sent_id&quot;</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="mi">1</span><span class="p">),</span>
-                          <span class="n">dict_file</span><span class="o">=</span><span class="n">trg_dict_path</span><span class="p">,</span>
-                          <span class="n">result_file</span><span class="o">=</span><span class="n">gen_trans_file</span><span class="p">)</span>
-<span class="n">outputs</span><span class="p">(</span><span class="n">beam_gen</span><span class="p">)</span>
+<span class="n">beam_gen</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">beam_search</span><span class="p">(</span>
+        <span class="n">name</span><span class="o">=</span><span class="n">decoder_group_name</span><span class="p">,</span>
+        <span class="n">step</span><span class="o">=</span><span class="n">gru_decoder_with_attention</span><span class="p">,</span>
+        <span class="nb">input</span><span class="o">=</span><span class="n">group_inputs</span><span class="p">,</span>
+        <span class="n">bos_id</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="c1"># Beginnning token.</span>
+        <span class="n">eos_id</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="c1"># End of sentence token.</span>
+        <span class="n">beam_size</span><span class="o">=</span><span class="n">beam_size</span><span class="p">,</span>
+        <span class="n">max_length</span><span class="o">=</span><span class="n">max_length</span><span class="p">)</span>
+
+<span class="k">return</span> <span class="n">beam_gen</span>
 </pre></div>
 </div>
-<p>注意，这种生成技术只用于类似解码器的生成过程。如果你正在处理序列标记任务，请参阅 <span class="xref std std-ref">semantic_role_labeling</span> 了解更多详细信息。</p>
-<p>完整的配置文件在<code class="docutils literal"><span class="pre">demo/seqToseq/seqToseq_net.py</span></code>。</p>
+<p>注意，这种生成技术只用于类似解码器的生成过程。如果你正在处理序列标记任务，请参阅 <a class="reference external" href="https://github.com/PaddlePaddle/book/tree/develop/06.understand_sentiment">book/06.understand_sentiment</a> 了解更多详细信息。</p>
+<p>完整的配置文件在 <a class="reference external" href="https://github.com/PaddlePaddle/book/blob/develop/08.machine_translation/train.py">book/08.machine_translation/train.py</a> 。</p>
 </div>
 </div>
 
@@ -432,6 +428,15 @@ attention，门控循环单元单步函数和输出函数：</p>
           </div>
           <footer>
   
+    <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
+      
+        <a href="recurrent_group_cn.html" class="btn btn-neutral float-right" title="Recurrent Group教程" accesskey="n">Next <span class="fa fa-arrow-circle-right"></span></a>
+      
+      
+        <a href="index_cn.html" class="btn btn-neutral" title="RNN相关模型" accesskey="p"><span class="fa fa-arrow-circle-left"></span> Previous</a>
+      
+    </div>
+  
 
   <hr/>
 

develop/doc_cn/howto/dev/contribute_to_paddle_cn.html

@@ -133,6 +133,7 @@
 <li class="toctree-l2"><a class="reference internal" href="write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2 current"><a class="current reference internal" href="#">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/howto/dev/new_layer_cn.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/howto/dev/write_docs_cn.html

@@ -133,6 +133,7 @@
 <li class="toctree-l2 current"><a class="current reference internal" href="#">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/howto/index_cn.html

@@ -132,6 +132,7 @@
 <li class="toctree-l2"><a class="reference internal" href="dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/howto/optimization/gpu_profiling_cn.html

@@ -133,6 +133,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/howto/usage/cluster/cluster_train_cn.html

@@ -133,6 +133,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/howto/usage/cmd_parameter/arguments_cn.html

@@ -133,6 +133,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/howto/usage/cmd_parameter/detail_introduction_cn.html

@@ -133,6 +133,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/howto/usage/cmd_parameter/index_cn.html

@@ -133,6 +133,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/howto/usage/cmd_parameter/use_case_cn.html

@@ -133,6 +133,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/howto/usage/k8s/k8s_basis_cn.html

@@ -133,6 +133,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/howto/usage/k8s/k8s_cn.html

@@ -133,6 +133,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/howto/usage/k8s/k8s_distributed_cn.html

@@ -133,6 +133,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/howto/usage/k8s/src/k8s_data/README.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../../../dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../../dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../../deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../../../deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../../deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../../deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../../deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/howto/usage/k8s/src/k8s_train/README.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../../../dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../../dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../../../deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../../../deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../../deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../../deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../../../deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/index_cn.html

@@ -131,6 +131,7 @@
 <li class="toctree-l2"><a class="reference internal" href="howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/search.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/tutorials/embedding_model/index_cn.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/tutorials/image_classification/index_cn.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/tutorials/imagenet_model/resnet_model_cn.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/tutorials/index_cn.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/tutorials/quick_start/index_cn.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/tutorials/rec/ml_dataset_cn.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/tutorials/rec/ml_regression_cn.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/tutorials/semantic_role_labeling/index_cn.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/tutorials/sentiment_analysis/index_cn.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>

develop/doc_cn/tutorials/text_generation/index_cn.html

@@ -130,6 +130,7 @@
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
 <li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
+<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
 <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>