diff --git a/fluid/face_detection/README_cn.md b/fluid/face_detection/README_cn.md
index 8987b00fb2c66daedd42993214b5c9bab42a99c3..a160fbd9ce25c4fac4333b9914058a16fda7e58a 100644
--- a/fluid/face_detection/README_cn.md
+++ b/fluid/face_detection/README_cn.md
@@ -93,13 +93,14 @@ tar -xf vgg_ilsvrc_16_fc_reduced.tar.gz && rm -f vgg_ilsvrc_16_fc_reduced.tar.gz
 `train.py` 是训练模块的主要执行程序，调用示例如下：
 
 ```bash
-python -u train.py --batch_size=12 --pretrained_model=vgg_ilsvrc_16_fc_reduced
+python -u train.py --batch_size=16 --pretrained_model=vgg_ilsvrc_16_fc_reduced
 ```
-  - 可以通过设置 `export CUDA_VISIBLE_DEVICES=0,1,2,3` 指定想要使用的GPU数量。
+  - 可以通过设置 `export CUDA_VISIBLE_DEVICES=0,1,2,3` 指定想要使用的GPU数量，`batch_size`默认设置为12或16。
   - 更多的可选参数见:
     ```bash
     python train.py --help
     ```
+  - 模型训练150轮以上可以收敛。用Nvidia Tesla P40 GPU 4卡并行，`batch_size=16`的配置，每轮训练大约40分钟，总共训练时长大约100小时
 
 模型训练所采用的数据增强：
 
@@ -152,8 +153,25 @@ python -u train.py --batch_size=12 --pretrained_model=vgg_ilsvrc_16_fc_reduced
 
   ```bash
   matlab -nodesktop -nosplash -nojvm -r "run wider_eval.m;quit;"
+
   ```
 
+### 模型预测以及可视化
+`widerface_eval.py`也可以用来做预测及可视化，调用示例如下：
+
+```bash
+python widerface_eval.py --infer=True --confs_threshold=0.15
+ --model_dir=output/159/ --image_path=data/WIDER_train/images/0--Parade/0_Parade_marchingband_1_219.jpg
+```
+下图可视化了模型的预测结果：
+<p align="center">
+<img src="images/0_Parade_marchingband_1_356.jpg" height=300 width=400 hspace='10'/>
+<img src="images/28_Sports_Fan_Sports_Fan_28_770.jpg" height=300 width=400 hspace='10'/>
+<img src="images/4_Dancing_Dancing_4_194.jpg" height=300 width=400 hspace='10'/>
+<img src="images/2_Demonstration_Demonstration_Or_Protest_2_58.jpg" height=300 width=400 hspace='10'/>  <br />
+Pyramidbox 预测可视化
+</p>
+
 ### 模型发布
 
 
diff --git a/fluid/face_detection/images/0_Parade_marchingband_1_356.jpg b/fluid/face_detection/images/0_Parade_marchingband_1_356.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..d5175c5a9d57184945ae63ab1cfc0a2621ef9b70
Binary files /dev/null and b/fluid/face_detection/images/0_Parade_marchingband_1_356.jpg differ
diff --git a/fluid/face_detection/images/28_Sports_Fan_Sports_Fan_28_770.jpg b/fluid/face_detection/images/28_Sports_Fan_Sports_Fan_28_770.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..661ad9abb2d21e6e6b872b2a44e14fc476e732e7
Binary files /dev/null and b/fluid/face_detection/images/28_Sports_Fan_Sports_Fan_28_770.jpg differ
diff --git a/fluid/face_detection/images/2_Demonstration_Demonstration_Or_Protest_2_58.jpg b/fluid/face_detection/images/2_Demonstration_Demonstration_Or_Protest_2_58.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..febe7411ae2ff258a608275fc9050294014e8342
Binary files /dev/null and b/fluid/face_detection/images/2_Demonstration_Demonstration_Or_Protest_2_58.jpg differ
diff --git a/fluid/face_detection/images/4_Dancing_Dancing_4_194.jpg b/fluid/face_detection/images/4_Dancing_Dancing_4_194.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..8161593708db628c6beb4f32c8133226e19f0f13
Binary files /dev/null and b/fluid/face_detection/images/4_Dancing_Dancing_4_194.jpg differ