Stash

doc_cn/algorithm/rnn/hrnn_rnn_api_compare.rst

@@ -139,20 +139,21 @@
 
 本例中的配置，使用了单层\ :ref:`glossary_RNN`\ 和\ :ref:`glossary_双层RNN`\ 使用一个\ :code:`recurrent_group`\ 将两个序列同时过完全连接的\ :ref:`glossary_RNN`\ 。对于单层\ :ref:`glossary_RNN`\ 的code如下。
 
-..  literalinclude:: ../../../paddle/gserver/tests/sequence_rnn_multi_unequalength_inputs.conf
+..  literalinclude:: ../../../paddle/gserver/tests/sequence_rnn_multi_unequalength_inputs.py
     :language: python
-    :lines: 41-58
+    :lines: 42-59
     :linenos:
 
 - 双层序列\：
 
   - 双层RNN中，对输入的两个特征分别求时序上的连续全连接(`inner_step1`和`inner_step2`分别处理fea1和fea2)，其功能与示例2中`sequence_nest_rnn.conf`的`outer_step`函数完全相同。不同之处是，此时输入`[SubsequenceInput(emb1), SubsequenceInput(emb2)]`在各时刻并不等长。
-  - 函数`outer_step`中可以分别处理这两个特征，但我们需要用<font color=red>targetInlink</font>指定recurrent_group的输出的格式（各子句长度）只能和其中一个保持一致，如这里选择了和emb2的长度一致。
+  - 函数`outer_step`中可以分别处理这两个特征，但我们需要用\ :red:`targetInlink`\ 指定recurrent_group的输出的格式（各子句长度）只能和其中一个保持一致，如这里选择了和emb2的长度一致。
   - 最后，依然是取encoder1_rep的最后一个时刻和encoder2_rep的所有时刻分别相加得到context。
 
-..  literalinclude:: ../../../paddle/gserver/tests/sequence_nest_rnn_multi_unequalength_inputs.conf
+..  literalinclude:: ../../../paddle/gserver/tests/sequence_nest_rnn_multi_unequalength_inputs.py
     :language: python
-    :lines: 41-89
+    :lines: 42-75, 82-89
+    :linenos:
 
 示例4：beam_search的生成
 ========================

paddle/gserver/tests/sequence_nest_rnn_multi_unequalength_inputs.py

-#edit-mode: -*- python -*-
+# edit-mode: -*- python -*-
 # Copyright (c) 2016 Baidu, Inc. All Rights Reserved
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
@@ -35,32 +35,22 @@ speaker2 = data_layer(name="word2", size=dict_dim)
 emb1 = embedding_layer(input=speaker1, size=word_dim)
 emb2 = embedding_layer(input=speaker2, size=word_dim)
 
-# This hierachical RNN is designed to be equivalent to the simple RNN in
-# sequence_rnn_multi_unequalength_inputs.conf
-
 
+# This hierarchical RNN is designed to be equivalent to the simple RNN in
+# sequence_rnn_multi_unequalength_inputs.conf
 def outer_step(x1, x2):
-    outer_mem1 = memory(name="outer_rnn_state1", size=hidden_dim)
-    outer_mem2 = memory(name="outer_rnn_state2", size=hidden_dim)
+    index = [0]
 
-    def inner_step1(y):
-        inner_mem = memory(
-            name='inner_rnn_state_' + y.name,
-            size=hidden_dim,
-            boot_layer=outer_mem1)
-        out = fc_layer(
-            input=[y, inner_mem],
-            size=hidden_dim,
-            act=TanhActivation(),
-            bias_attr=True,
-            name='inner_rnn_state_' + y.name)
-        return out
+    def inner_step(ipt):
+        index[0] += 1
+        i = index[0]
+        outer_mem = memory(name="outer_rnn_state_%d" % i, size=hidden_dim)
 
-    def inner_step2(y):
+        def inner_step_impl(y):
             inner_mem = memory(
-            name='inner_rnn_state_' + y.name,
+                name="inner_rnn_state_" + y.name,
                 size=hidden_dim,
-            boot_layer=outer_mem2)
+                boot_layer=outer_mem)
             out = fc_layer(
                 input=[y, inner_mem],
                 size=hidden_dim,
@@ -69,12 +59,13 @@ def outer_step(x1, x2):
                 name='inner_rnn_state_' + y.name)
             return out
 
-    encoder1 = recurrent_group(step=inner_step1, name='inner1', input=x1)
-
-    encoder2 = recurrent_group(step=inner_step2, name='inner2', input=x2)
+        encoder = recurrent_group(
+            step=inner_step_impl, name='inner_%d' % i, input=ipt)
+        last = last_seq(name="outer_rnn_state_%d" % i, input=encoder)
+        return encoder, last
 
-    sentence_last_state1 = last_seq(input=encoder1, name='outer_rnn_state1')
-    sentence_last_state2_ = last_seq(input=encoder2, name='outer_rnn_state2')
+    _, sentence_last_state1 = inner_step(ipt=x1)
+    encoder2, _ = inner_step(ipt=x2)
 
     encoder1_expand = expand_layer(
         input=sentence_last_state1, expand_as=encoder2)