update the machine translation demo.

08.machine_translation/README.cn.md

@@ -228,19 +228,19 @@ is_generating = False
    - 对源语言序列编码后的结果（见2的最后一步），过一个前馈神经网络（Feed Forward Neural Network），得到其映射。
 
    ```python
-    with paddle.layer.mixed(size=decoder_size) as encoded_proj:
-        encoded_proj += paddle.layer.full_matrix_projection(
-            input=encoded_vector)
+   encoded_proj = paddle.layer.mixed(
+       size=decoder_size,
+       input=paddle.layer.full_matrix_projection(encoded_vector))
    ```
 
    - 构造解码器RNN的初始状态。由于解码器需要预测时序目标序列，但在0时刻并没有初始值，所以我们希望对其进行初始化。这里采用的是将源语言序列逆序编码后的最后一个状态进行非线性映射，作为该初始值，即$c_0=h_T$。
 
    ```python
    backward_first = paddle.layer.first_seq(input=src_backward)
-    with paddle.layer.mixed(
-            size=decoder_size, act=paddle.activation.Tanh()) as decoder_boot:
-        decoder_boot += paddle.layer.full_matrix_projection(
-            input=backward_first)
+   decoder_boot = paddle.layer.mixed(
+       size=decoder_size,
+       act=paddle.activation.Tanh(),
+       input=paddle.layer.full_matrix_projection(backward_first))
    ```
 
    - 定义解码阶段每一个时间步的RNN行为，即根据当前时刻的源语言上下文向量$c_i$、解码器隐层状态$z_i$和目标语言中第$i$个词$u_i$，来预测第$i+1$个词的概率$p_{i+1}$。
@@ -252,7 +252,6 @@ is_generating = False
 
    ```python
    def gru_decoder_with_attention(enc_vec, enc_proj, current_word):
-
         decoder_mem = paddle.layer.memory(
             name='gru_decoder', size=decoder_size, boot_layer=decoder_boot)
 
@@ -261,10 +260,12 @@ is_generating = False
             encoded_proj=enc_proj,
             decoder_state=decoder_mem)
 
-        with paddle.layer.mixed(size=decoder_size * 3) as decoder_inputs:
-            decoder_inputs += paddle.layer.full_matrix_projection(input=context)
-            decoder_inputs += paddle.layer.full_matrix_projection(
-                input=current_word)
+        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)
+            ])
 
         gru_step = paddle.layer.gru_step(
             name='gru_decoder',
@@ -272,11 +273,11 @@ is_generating = False
             output_mem=decoder_mem,
             size=decoder_size)
 
-        with paddle.layer.mixed(
+        out = paddle.layer.mixed(
             size=target_dict_dim,
             bias_attr=True,
-                act=paddle.activation.Softmax()) as out:
-            out += paddle.layer.full_matrix_projection(input=gru_step)
+            act=paddle.activation.Softmax(),
+            input=paddle.layer.full_matrix_projection(input=gru_step))
         return out
    ```
 
@@ -284,8 +285,8 @@ is_generating = False
 
     ```python
     decoder_group_name = "decoder_group"
-    group_input1 = paddle.layer.StaticInputV2(input=encoded_vector, is_seq=True)
-    group_input2 = paddle.layer.StaticInputV2(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]
     ```
 
@@ -338,7 +339,7 @@ is_generating = False
        # GeneratedInputs, which is initialized by a start mark, such as <s>,
        # and must be included in generation.
 
-       trg_embedding = paddle.layer.GeneratedInputV2(
+       trg_embedding = paddle.layer.GeneratedInput(
            size=target_dict_dim,
            embedding_name='_target_language_embedding',
            embedding_size=word_vector_dim)

08.machine_translation/README.md

@@ -265,19 +265,19 @@ is_generating = False
    - Get a projection of the encoding (c.f. 2.3) of the source language sequence by passing it into a feed forward neural network
 
    ```python
-    with paddle.layer.mixed(size=decoder_size) as encoded_proj:
-        encoded_proj += paddle.layer.full_matrix_projection(
-            input=encoded_vector)
+   encoded_proj = paddle.layer.mixed(
+       size=decoder_size,
+       input=paddle.layer.full_matrix_projection(encoded_vector))
    ```
 
    - Use a non-linear transformation of the last hidden state of the backward GRU on the source language sentence as the initial state of the decoder RNN $c_0=h_T$
 
    ```python
    backward_first = paddle.layer.first_seq(input=src_backward)
-    with paddle.layer.mixed(
-            size=decoder_size, act=paddle.activation.Tanh()) as decoder_boot:
-        decoder_boot += paddle.layer.full_matrix_projection(
-            input=backward_first)
+   decoder_boot = paddle.layer.mixed(
+       size=decoder_size,
+       act=paddle.activation.Tanh(),
+       input=paddle.layer.full_matrix_projection(backward_first))
    ```
 
    - Define the computation in each time step for the decoder RNN, i.e., according to the current context vector $c_i$, hidden state for the decoder $z_i$ and the $i$-th word $u_i$ in the target language to predict the probability $p_{i+1}$ for the $i+1$-th word.
@@ -290,7 +290,6 @@ is_generating = False
 
    ```python
    def gru_decoder_with_attention(enc_vec, enc_proj, current_word):
-
         decoder_mem = paddle.layer.memory(
             name='gru_decoder', size=decoder_size, boot_layer=decoder_boot)
 
@@ -299,10 +298,12 @@ is_generating = False
             encoded_proj=enc_proj,
             decoder_state=decoder_mem)
 
-        with paddle.layer.mixed(size=decoder_size * 3) as decoder_inputs:
-            decoder_inputs += paddle.layer.full_matrix_projection(input=context)
-            decoder_inputs += paddle.layer.full_matrix_projection(
-                input=current_word)
+        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)
+            ])
 
         gru_step = paddle.layer.gru_step(
             name='gru_decoder',
@@ -310,11 +311,11 @@ is_generating = False
             output_mem=decoder_mem,
             size=decoder_size)
 
-        with paddle.layer.mixed(
+        out = paddle.layer.mixed(
             size=target_dict_dim,
             bias_attr=True,
-                act=paddle.activation.Softmax()) as out:
-            out += paddle.layer.full_matrix_projection(input=gru_step)
+            act=paddle.activation.Softmax(),
+            input=paddle.layer.full_matrix_projection(input=gru_step))
         return out
    ```
 
@@ -322,8 +323,8 @@ is_generating = False
 
     ```python
     decoder_group_name = "decoder_group"
-    group_input1 = paddle.layer.StaticInputV2(input=encoded_vector, is_seq=True)
-    group_input2 = paddle.layer.StaticInputV2(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]
     ```
 
@@ -376,7 +377,7 @@ is_generating = False
        # GeneratedInputs, which is initialized by a start mark, such as <s>,
        # and must be included in generation.
 
-       trg_embedding = paddle.layer.GeneratedInputV2(
+       trg_embedding = paddle.layer.GeneratedInput(
            size=target_dict_dim,
            embedding_name='_target_language_embedding',
            embedding_size=word_vector_dim)

08.machine_translation/index.cn.html

@@ -270,19 +270,19 @@ is_generating = False
    - 对源语言序列编码后的结果（见2的最后一步），过一个前馈神经网络（Feed Forward Neural Network），得到其映射。
 
    ```python
-    with paddle.layer.mixed(size=decoder_size) as encoded_proj:
-        encoded_proj += paddle.layer.full_matrix_projection(
-            input=encoded_vector)
+   encoded_proj = paddle.layer.mixed(
+       size=decoder_size,
+       input=paddle.layer.full_matrix_projection(encoded_vector))
    ```
 
    - 构造解码器RNN的初始状态。由于解码器需要预测时序目标序列，但在0时刻并没有初始值，所以我们希望对其进行初始化。这里采用的是将源语言序列逆序编码后的最后一个状态进行非线性映射，作为该初始值，即$c_0=h_T$。
 
    ```python
    backward_first = paddle.layer.first_seq(input=src_backward)
-    with paddle.layer.mixed(
-            size=decoder_size, act=paddle.activation.Tanh()) as decoder_boot:
-        decoder_boot += paddle.layer.full_matrix_projection(
-            input=backward_first)
+   decoder_boot = paddle.layer.mixed(
+       size=decoder_size,
+       act=paddle.activation.Tanh(),
+       input=paddle.layer.full_matrix_projection(backward_first))
    ```
 
    - 定义解码阶段每一个时间步的RNN行为，即根据当前时刻的源语言上下文向量$c_i$、解码器隐层状态$z_i$和目标语言中第$i$个词$u_i$，来预测第$i+1$个词的概率$p_{i+1}$。
@@ -294,7 +294,6 @@ is_generating = False
 
    ```python
    def gru_decoder_with_attention(enc_vec, enc_proj, current_word):
-
         decoder_mem = paddle.layer.memory(
             name='gru_decoder', size=decoder_size, boot_layer=decoder_boot)
 
@@ -303,10 +302,12 @@ is_generating = False
             encoded_proj=enc_proj,
             decoder_state=decoder_mem)
 
-        with paddle.layer.mixed(size=decoder_size * 3) as decoder_inputs:
-            decoder_inputs += paddle.layer.full_matrix_projection(input=context)
-            decoder_inputs += paddle.layer.full_matrix_projection(
-                input=current_word)
+        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)
+            ])
 
         gru_step = paddle.layer.gru_step(
             name='gru_decoder',
@@ -314,11 +315,11 @@ is_generating = False
             output_mem=decoder_mem,
             size=decoder_size)
 
-        with paddle.layer.mixed(
+        out = paddle.layer.mixed(
             size=target_dict_dim,
             bias_attr=True,
-                act=paddle.activation.Softmax()) as out:
-            out += paddle.layer.full_matrix_projection(input=gru_step)
+            act=paddle.activation.Softmax(),
+            input=paddle.layer.full_matrix_projection(input=gru_step))
         return out
    ```
 
@@ -326,8 +327,8 @@ is_generating = False
 
     ```python
     decoder_group_name = "decoder_group"
-    group_input1 = paddle.layer.StaticInputV2(input=encoded_vector, is_seq=True)
-    group_input2 = paddle.layer.StaticInputV2(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]
     ```
 
@@ -380,7 +381,7 @@ is_generating = False
        # GeneratedInputs, which is initialized by a start mark, such as <s>,
        # and must be included in generation.
 
-       trg_embedding = paddle.layer.GeneratedInputV2(
+       trg_embedding = paddle.layer.GeneratedInput(
            size=target_dict_dim,
            embedding_name='_target_language_embedding',
            embedding_size=word_vector_dim)

08.machine_translation/index.html

@@ -307,19 +307,19 @@ is_generating = False
    - Get a projection of the encoding (c.f. 2.3) of the source language sequence by passing it into a feed forward neural network
 
    ```python
-    with paddle.layer.mixed(size=decoder_size) as encoded_proj:
-        encoded_proj += paddle.layer.full_matrix_projection(
-            input=encoded_vector)
+   encoded_proj = paddle.layer.mixed(
+       size=decoder_size,
+       input=paddle.layer.full_matrix_projection(encoded_vector))
    ```
 
    - Use a non-linear transformation of the last hidden state of the backward GRU on the source language sentence as the initial state of the decoder RNN $c_0=h_T$
 
    ```python
    backward_first = paddle.layer.first_seq(input=src_backward)
-    with paddle.layer.mixed(
-            size=decoder_size, act=paddle.activation.Tanh()) as decoder_boot:
-        decoder_boot += paddle.layer.full_matrix_projection(
-            input=backward_first)
+   decoder_boot = paddle.layer.mixed(
+       size=decoder_size,
+       act=paddle.activation.Tanh(),
+       input=paddle.layer.full_matrix_projection(backward_first))
    ```
 
    - Define the computation in each time step for the decoder RNN, i.e., according to the current context vector $c_i$, hidden state for the decoder $z_i$ and the $i$-th word $u_i$ in the target language to predict the probability $p_{i+1}$ for the $i+1$-th word.
@@ -332,7 +332,6 @@ is_generating = False
 
    ```python
    def gru_decoder_with_attention(enc_vec, enc_proj, current_word):
-
         decoder_mem = paddle.layer.memory(
             name='gru_decoder', size=decoder_size, boot_layer=decoder_boot)
 
@@ -341,10 +340,12 @@ is_generating = False
             encoded_proj=enc_proj,
             decoder_state=decoder_mem)
 
-        with paddle.layer.mixed(size=decoder_size * 3) as decoder_inputs:
-            decoder_inputs += paddle.layer.full_matrix_projection(input=context)
-            decoder_inputs += paddle.layer.full_matrix_projection(
-                input=current_word)
+        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)
+            ])
 
         gru_step = paddle.layer.gru_step(
             name='gru_decoder',
@@ -352,11 +353,11 @@ is_generating = False
             output_mem=decoder_mem,
             size=decoder_size)
 
-        with paddle.layer.mixed(
+        out = paddle.layer.mixed(
             size=target_dict_dim,
             bias_attr=True,
-                act=paddle.activation.Softmax()) as out:
-            out += paddle.layer.full_matrix_projection(input=gru_step)
+            act=paddle.activation.Softmax(),
+            input=paddle.layer.full_matrix_projection(input=gru_step))
         return out
    ```
 
@@ -364,8 +365,8 @@ is_generating = False
 
     ```python
     decoder_group_name = "decoder_group"
-    group_input1 = paddle.layer.StaticInputV2(input=encoded_vector, is_seq=True)
-    group_input2 = paddle.layer.StaticInputV2(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]
     ```
 
@@ -418,7 +419,7 @@ is_generating = False
        # GeneratedInputs, which is initialized by a start mark, such as <s>,
        # and must be included in generation.
 
-       trg_embedding = paddle.layer.GeneratedInputV2(
+       trg_embedding = paddle.layer.GeneratedInput(
            size=target_dict_dim,
            embedding_name='_target_language_embedding',
            embedding_size=word_vector_dim)

08.machine_translation/train.py

@@ -27,16 +27,16 @@ def seqToseq_net(source_dict_dim, target_dict_dim, is_generating=False):
     encoded_vector = paddle.layer.concat(input=[src_forward, src_backward])
 
     #### Decoder
-    with paddle.layer.mixed(size=decoder_size) as encoded_proj:
-        encoded_proj += paddle.layer.full_matrix_projection(
-            input=encoded_vector)
+    encoded_proj = paddle.layer.mixed(
+        size=decoder_size,
+        input=paddle.layer.full_matrix_projection(encoded_vector))
 
     backward_first = paddle.layer.first_seq(input=src_backward)
 
-    with paddle.layer.mixed(
-            size=decoder_size, act=paddle.activation.Tanh()) as decoder_boot:
-        decoder_boot += paddle.layer.full_matrix_projection(
-            input=backward_first)
+    decoder_boot = paddle.layer.mixed(
+        size=decoder_size,
+        act=paddle.activation.Tanh(),
+        input=paddle.layer.full_matrix_projection(backward_first))
 
     def gru_decoder_with_attention(enc_vec, enc_proj, current_word):
 
@@ -48,10 +48,12 @@ def seqToseq_net(source_dict_dim, target_dict_dim, is_generating=False):
             encoded_proj=enc_proj,
             decoder_state=decoder_mem)
 
-        with paddle.layer.mixed(size=decoder_size * 3) as decoder_inputs:
-            decoder_inputs += paddle.layer.full_matrix_projection(input=context)
-            decoder_inputs += paddle.layer.full_matrix_projection(
-                input=current_word)
+        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)
+            ])
 
         gru_step = paddle.layer.gru_step(
             name='gru_decoder',
@@ -59,16 +61,16 @@ def seqToseq_net(source_dict_dim, target_dict_dim, is_generating=False):
             output_mem=decoder_mem,
             size=decoder_size)
 
-        with paddle.layer.mixed(
+        out = paddle.layer.mixed(
             size=target_dict_dim,
             bias_attr=True,
-                act=paddle.activation.Softmax()) as out:
-            out += paddle.layer.full_matrix_projection(input=gru_step)
+            act=paddle.activation.Softmax(),
+            input=paddle.layer.full_matrix_projection(input=gru_step))
         return out
 
     decoder_group_name = "decoder_group"
-    group_input1 = paddle.layer.StaticInputV2(input=encoded_vector, is_seq=True)
-    group_input2 = paddle.layer.StaticInputV2(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]
 
     if not is_generating:
@@ -106,7 +108,7 @@ def seqToseq_net(source_dict_dim, target_dict_dim, is_generating=False):
         # GeneratedInputs, which is initialized by a start mark, such as <s>,
         # and must be included in generation.
 
-        trg_embedding = paddle.layer.GeneratedInputV2(
+        trg_embedding = paddle.layer.GeneratedInput(
             size=target_dict_dim,
             embedding_name='_target_language_embedding',
             embedding_size=word_vector_dim)