Merge pull request #534 from peterzhang2029/dssm_fix

Fix the output of cnn in DSSM.

Author: peterzhang2029

dssm/README.cn.md

@@ -131,7 +131,7 @@ def create_cnn(self, emb, prefix=''):
 
     conv_3 = create_conv(3, self.dnn_dims[1], "cnn")
     conv_4 = create_conv(4, self.dnn_dims[1], "cnn")
-    return conv_3, conv_4
+    return paddle.layer.concat(input=[conv_3, conv_4])
 ```
 
 CNN 接受词向量序列，通过卷积和池化操作捕捉到原始句子的关键信息，最终输出一个语义向量（可以认为是句子向量）。
@@ -263,7 +263,7 @@ Pairwise Rank复用上面的DNN结构，同一个source对两个target求相似
 
 ## 执行训练
 
-可以直接执行 `python train.py -y 0 --model_arch 0` 使用 `./data/classification` 目录里的实例数据来测试能否直接运行训练分类FC模型。
+可以直接执行 `python train.py -y 0 --model_arch 0 --class_num 2` 使用 `./data/classification` 目录里的实例数据来测试能否直接运行训练分类FC模型。
 
 其他模型结构也可以通过命令行实现定制，详细命令行参数请执行 `python train.py --help`进行查阅。
 

dssm/README.md

@@ -107,7 +107,7 @@ def create_cnn(self, emb, prefix=''):
 
     conv_3 = create_conv(3, self.dnn_dims[1], "cnn")
     conv_4 = create_conv(4, self.dnn_dims[1], "cnn")
-    return conv_3, conv_4
+    return paddle.layer.concat(input=[conv_3, conv_4])
 ```
 
 CNN accepts the word sequence of the embedding table, then process the data by convolution and pooling, and finally outputs a semantic vector.
@@ -240,12 +240,12 @@ The example of this format is as follows.
 
 ## Training
 
-We use `python train.py -y 0 --model_arch 0` with the data in  `./data/classification` to train a DSSM model for classification. The paremeters to execute the script `train.py` can be found by execution `python infer.py --help`. Some important parameters are：
+We use `python train.py -y 0 --model_arch 0 --class_num 2` with the data in  `./data/classification` to train a DSSM model for classification. The paremeters to execute the script `train.py` can be found by execution `python infer.py --help`. Some important parameters are：
 
 - `train_data_path` Training data path
 - `test_data_path`  Test data path, optional
 - `source_dic_path`  Source dictionary path
-- `target_dic_path` 目Target dictionary path
+- `target_dic_path` Target dictionary path
 - `model_type`  The type of loss function of the model: classification 0, sort 1, regression 2
 - `model_arch` Model structure: FC 0，CNN 1, RNN 2
 - `dnn_dims` The dimension of each layer of the model is set, the default is `256,128,64,32`，with 4 layers.

dssm/network_conf.py

@@ -146,12 +146,12 @@ def create_conv(context_len, hidden_size, prefix):
                 pool_bias_attr=ParamAttr(name=key + "_pool.b"))
             return conv
 
-        logger.info("create a sequence_conv_pool which context width is 3")
+        logger.info("create a sequence_conv_pool whose context width is 3.")
         conv_3 = create_conv(3, self.dnn_dims[1], "cnn")
-        logger.info("create a sequence_conv_pool which context width is 4")
+        logger.info("create a sequence_conv_pool whose context width is 4.")
         conv_4 = create_conv(4, self.dnn_dims[1], "cnn")
 
-        return conv_3, conv_4
+        return paddle.layer.concat(input=[conv_3, conv_4])
 
     def create_dnn(self, sent_vec, prefix):
         # if more than three layers, than a fc layer will be added.