diff --git a/tensorflow2fluid/doc/tf.contrib.layers.flatten b/tensorflow2fluid/doc/tf.contrib.layers.flatten
new file mode 100644
index 0000000000000000000000000000000000000000..225f719f94d452774a832fc17e1a05d4012e8cf1
--- /dev/null
+++ b/tensorflow2fluid/doc/tf.contrib.layers.flatten
@@ -0,0 +1,37 @@
+## tf.contrib.layers.flatten
+
+### [tf.contrib.layers.flatten](https://www.tensorflow.org/api_docs/python/tf/contrib/layers/flatten)
+
+```python
+tf.contrib.layers.flatten(
+    inputs,
+    outputs_collections=None,
+    scope=None
+)
+```
+
+### [paddle.fluid.layers.flatten](http://paddlepaddle.org/documentation/docs/zh/1.2/api_cn/layers_cn.html#flatten)
+
+```python
+paddle.fluid.layers.flatten(
+    x, 
+    axis=1, 
+    name=None
+)
+```
+
+### 功能差异
+
+#### 计算方式
+
+TensorFlow：固定第0维，将其他维合并；  
+
+PaddlePaddle：使用`axis`指定两次合并的维度边界，参考下面示例。
+
+### 代码示例
+```
+# 张量x的shape为 [2, 3, 4, 5]
+out = fluid.layers.flatten(x, axis=2)
+out.shape # [2*3, 4*5]
+
+```