diff --git a/06.understand_sentiment/README.cn.md b/06.understand_sentiment/README.cn.md
index d7b80d80264828aa43e5333d6976504f8716e9ca..4bacddb4b17317b2ca17b8445c1d7624baa2da8f 100644
--- a/06.understand_sentiment/README.cn.md
+++ b/06.understand_sentiment/README.cn.md
@@ -257,6 +257,9 @@ train_reader = paddle.batch(
     paddle.reader.shuffle(
         paddle.dataset.imdb.train(word_dict), buf_size=25000),
     batch_size=BATCH_SIZE)
+print("Reading testing data....")
+test_reader = paddle.batch(
+    paddle.dataset.imdb.test(word_dict), batch_size=BATCH_SIZE)
 ```
 word_dict是一个字典序列，是词和label的对应关系，运行下一行可以看到具体内容：
 ```python
@@ -275,6 +278,28 @@ sgd_optimizer = optimizer_func()#训练优化函数
 sgd_optimizer.minimize(avg_cost)
 ```
 
+该函数用来计算训练中模型在test数据集上的结果
+```python
+def train_test(program, reader):
+    count = 0
+    feed_var_list = [
+        program.global_block().var(var_name) for var_name in feed_order
+    ]
+    feeder_test = fluid.DataFeeder(feed_list=feed_var_list, place=place)
+    test_exe = fluid.Executor(place)
+    accumulated = len([avg_cost, accuracy]) * [0]
+    for test_data in reader():
+        avg_cost_np = test_exe.run(
+            program=program,
+            feed=feeder_test.feed(test_data),
+            fetch_list=[avg_cost, accuracy])
+        accumulated = [
+            x[0] + x[1][0] for x in zip(accumulated, avg_cost_np)
+        ]
+        count += 1
+    return [x / count for x in accumulated]
+```
+
 ### 提供数据并构建主训练循环
 
 `feed_order`用来定义每条产生的数据和`fluid.layers.data`之间的映射关系。比如，`imdb.train`产生的第一列的数据对应的是`words`这个特征。
@@ -379,7 +404,7 @@ with fluid.scope_guard(inference_scope):
      fetch_targets] = fluid.io.load_inference_model(params_dirname, exe)
 
     assert feed_target_names[0] == "words"
-    results = exe.run(inference_program,
+    results = exe.run(inferencer,
                       feed={feed_target_names[0]: tensor_words},
                       fetch_list=fetch_targets,
                       return_numpy=False)
diff --git a/06.understand_sentiment/index.cn.html b/06.understand_sentiment/index.cn.html
index f1817c137359047d628e4f1cbe0fe0c6e84096e1..c60892e5ed94e0089db63bc99ced9d6fd5595eba 100644
--- a/06.understand_sentiment/index.cn.html
+++ b/06.understand_sentiment/index.cn.html
@@ -299,6 +299,9 @@ train_reader = paddle.batch(
     paddle.reader.shuffle(
         paddle.dataset.imdb.train(word_dict), buf_size=25000),
     batch_size=BATCH_SIZE)
+print("Reading testing data....")
+test_reader = paddle.batch(
+    paddle.dataset.imdb.test(word_dict), batch_size=BATCH_SIZE)
 ```
 word_dict是一个字典序列，是词和label的对应关系，运行下一行可以看到具体内容：
 ```python
@@ -317,6 +320,28 @@ sgd_optimizer = optimizer_func()#训练优化函数
 sgd_optimizer.minimize(avg_cost)
 ```
 
+该函数用来计算训练中模型在test数据集上的结果
+```python
+def train_test(program, reader):
+    count = 0
+    feed_var_list = [
+        program.global_block().var(var_name) for var_name in feed_order
+    ]
+    feeder_test = fluid.DataFeeder(feed_list=feed_var_list, place=place)
+    test_exe = fluid.Executor(place)
+    accumulated = len([avg_cost, accuracy]) * [0]
+    for test_data in reader():
+        avg_cost_np = test_exe.run(
+            program=program,
+            feed=feeder_test.feed(test_data),
+            fetch_list=[avg_cost, accuracy])
+        accumulated = [
+            x[0] + x[1][0] for x in zip(accumulated, avg_cost_np)
+        ]
+        count += 1
+    return [x / count for x in accumulated]
+```
+
 ### 提供数据并构建主训练循环
 
 `feed_order`用来定义每条产生的数据和`fluid.layers.data`之间的映射关系。比如，`imdb.train`产生的第一列的数据对应的是`words`这个特征。
@@ -421,7 +446,7 @@ with fluid.scope_guard(inference_scope):
      fetch_targets] = fluid.io.load_inference_model(params_dirname, exe)
 
     assert feed_target_names[0] == "words"
-    results = exe.run(inference_program,
+    results = exe.run(inferencer,
                       feed={feed_target_names[0]: tensor_words},
                       fetch_list=fetch_targets,
                       return_numpy=False)