diff --git a/fluid/README.md b/fluid/README.md
index e8417d2b542cf262ce13d5dbc095bde3ba851f29..2da327bec4a70f0d4f2176f9257797960da64adb 100644
--- a/fluid/README.md
+++ b/fluid/README.md
@@ -28,8 +28,11 @@ Fluid模型配置和参数文件的工具。
 
 开放环境中的检测人脸，尤其是小的、模糊的和部分遮挡的人脸也是一个具有挑战的任务。我们也介绍了如何基于 [WIDER FACE](http://mmlab.ie.cuhk.edu.hk/projects/WIDERFace) 数据训练百度自研的人脸检测PyramidBox模型，该算法于2018年3月份在WIDER FACE的多项评测中均获得 [第一名](http://mmlab.ie.cuhk.edu.hk/projects/WIDERFace/WiderFace_Results.html)。
 
+Faster RCNN 是典型的两阶段目标检测器，相较于传统提取区域的方法，Faster RCNN中RPN网络通过共享卷积层参数大幅提高提取区域的效率，并提出高质量的候选区域。
+
 -  [Single Shot MultiBox Detector](https://github.com/PaddlePaddle/models/blob/develop/fluid/object_detection/README_cn.md)
 -  [Face Detector: PyramidBox](https://github.com/PaddlePaddle/models/tree/develop/fluid/face_detection/README_cn.md)
+-  [Faster RCNN](https://github.com/PaddlePaddle/models/tree/develop/fluid/faster_rcnn/README_cn.md)
 
 图像语义分割
 ------------
diff --git a/fluid/faster_rcnn/README.md b/fluid/faster_rcnn/README.md
index 99438c6768197238d7889d8c63e1e8bdbfde0202..617a103278e29c22e5aef73830605522159b4a86 100644
--- a/fluid/faster_rcnn/README.md
+++ b/fluid/faster_rcnn/README.md
@@ -43,7 +43,7 @@ After data preparation, one can start the training step by:
 
     python train.py \
        --max_size=1333 \
-       --scales=800 \
+       --scales=[800] \
        --batch_size=8 \
        --model_save_dir=output/
 
@@ -58,6 +58,21 @@ After data preparation, one can start the training step by:
 
 Set `pretrained_model` to load pre-trained model. In addition, this parameter is used to load trained model when finetuning as well.
 
+**Install the [cocoapi](https://github.com/cocodataset/cocoapi):**
+
+To train the model, [cocoapi](https://github.com/cocodataset/cocoapi) is needed. Install the cocoapi:
+
+    # COCOAPI=/path/to/clone/cocoapi
+    git clone https://github.com/cocodataset/cocoapi.git $COCOAPI
+    cd $COCOAPI/PythonAPI
+    # if cython is not installed
+    pip install Cython
+    # Install into global site-packages
+    make install
+    # Alternatively, if you do not have permissions or prefer
+    # not to install the COCO API into global site-packages
+    python2 setup.py install --user
+
 **data reader introduction:**
 
 * Data reader is defined in `reader.py`.
@@ -103,18 +118,7 @@ Finetuning is to finetune model weights in a specific task by loading pretrained
 
 ## Evaluation
 
-Evaluation is to evaluate the performance of a trained model. This sample provides `eval_coco_map.py` which uses a COCO-specific mAP metric defined by [COCO committee](http://cocodataset.org/#detections-eval). To use `eval_coco_map.py` , [cocoapi](https://github.com/cocodataset/cocoapi) is needed. Install the cocoapi:
-
-    # COCOAPI=/path/to/clone/cocoapi
-    git clone https://github.com/cocodataset/cocoapi.git $COCOAPI
-    cd $COCOAPI/PythonAPI
-    # if cython is not installed
-    pip install Cython
-    # Install into global site-packages
-    make install
-    # Alternatively, if you do not have permissions or prefer
-    # not to install the COCO API into global site-packages
-    python2 setup.py install --user
+Evaluation is to evaluate the performance of a trained model. This sample provides `eval_coco_map.py` which uses a COCO-specific mAP metric defined by [COCO committee](http://cocodataset.org/#detections-eval).
 
 `eval_coco_map.py` is the main executor for evalution, one can start evalution step by:
 
@@ -136,7 +140,7 @@ Faster RCNN mAP
 | Detectron                 | 8            |    180000        | 0.315 |
 | Fluid minibatch padding | 8            |    180000        | 0.314 |
 | Fluid all padding         | 8            |    180000        | 0.308 |
-| Fluid no padding         |6            |    240000        | 0.317 |
+| Fluid no padding         |8            |    180000        | 0.316 |
 
 * Fluid all padding: Each image padding to 1333\*1333.
 * Fluid minibatch padding: Images in one batch padding to the same size. This method is same as detectron.
diff --git a/fluid/faster_rcnn/README_cn.md b/fluid/faster_rcnn/README_cn.md
index cd238a86c8ec82f1519280c5552699c1b75438ec..6f9e892e6b64008fdf23bc53466d504d04266fb7 100644
--- a/fluid/faster_rcnn/README_cn.md
+++ b/fluid/faster_rcnn/README_cn.md
@@ -42,7 +42,7 @@ Faster RCNN 目标检测模型
 
     python train.py \
        --max_size=1333 \
-       --scales=800 \
+       --scales=[800] \
        --batch_size=8 \
        --model_save_dir=output/ \
        --pretrained_model=${path_to_pretrain_model}
@@ -58,6 +58,21 @@ Faster RCNN 目标检测模型
 
 通过初始化`pretrained_model` 加载预训练模型。同时在参数微调时也采用该设置加载已训练模型。
 
+**安装[cocoapi](https://github.com/cocodataset/cocoapi)：**
+
+训练前需要首先下载[cocoapi](https://github.com/cocodataset/cocoapi)：
+
+    # COCOAPI=/path/to/clone/cocoapi
+    git clone https://github.com/cocodataset/cocoapi.git $COCOAPI
+    cd $COCOAPI/PythonAPI
+    # if cython is not installed
+    pip install Cython
+    # Install into global site-packages
+    make install
+    # Alternatively, if you do not have permissions or prefer
+    # not to install the COCO API into global site-packages
+    python2 setup.py install --user
+
 **数据读取器说明：** 数据读取器定义在reader.py中。所有图像将短边等比例缩放至`scales`，若长边大于`max_size`, 则再次将长边等比例缩放至`max_iter`。在训练阶段，对图像采用水平翻转。支持将同一个batch内的图像padding为相同尺寸。
 
 **模型设置：**
@@ -87,18 +102,7 @@ Faster RCNN 训练loss
 
 ## 模型评估
 
-模型评估是指对训练完毕的模型评估各类性能指标。本示例采用[COCO官方评估](http://cocodataset.org/#detections-eval)，使用前需要首先下载[cocoapi](https://github.com/cocodataset/cocoapi)：
-
-    # COCOAPI=/path/to/clone/cocoapi
-    git clone https://github.com/cocodataset/cocoapi.git $COCOAPI
-    cd $COCOAPI/PythonAPI
-    # if cython is not installed
-    pip install Cython
-    # Install into global site-packages
-    make install
-    # Alternatively, if you do not have permissions or prefer
-    # not to install the COCO API into global site-packages
-    python2 setup.py install --user
+模型评估是指对训练完毕的模型评估各类性能指标。本示例采用[COCO官方评估](http://cocodataset.org/#detections-eval)
 
 `eval_coco_map.py`是评估模块的主要执行程序，调用示例如下：
 
@@ -120,7 +124,7 @@ Faster RCNN mAP
 | Detectron                 | 8            |    180000        | 0.315 |
 | Fluid minibatch padding | 8            |    180000        | 0.314 |
 | Fluid all padding         | 8            |    180000        | 0.308 |
-| Fluid no padding            |6            |    240000        | 0.317 |
+| Fluid no padding            |8            |    180000        | 0.316 |
 
 * Fluid all padding: 每张图像填充为1333\*1333大小。
 * Fluid minibatch padding: 同一个batch内的图像填充为相同尺寸。该方法与detectron处理相同。
diff --git a/fluid/faster_rcnn/image/mAP.jpg b/fluid/faster_rcnn/image/mAP.jpg
index 9202f8f1a06200c2e9c111eac562c2d59b460cb9..9c781a7caef808b716ace077b2f202267e790f76 100644
Binary files a/fluid/faster_rcnn/image/mAP.jpg and b/fluid/faster_rcnn/image/mAP.jpg differ
diff --git a/fluid/faster_rcnn/image/train_loss.jpg b/fluid/faster_rcnn/image/train_loss.jpg
index 75d4b0a5f02aacd8fb3a0dfa7a62e60fac9ccb6b..3cc0ff84b30599597bf6a66bf0cbfd7789c485f0 100644
Binary files a/fluid/faster_rcnn/image/train_loss.jpg and b/fluid/faster_rcnn/image/train_loss.jpg differ