diff --git a/PaddleCV/human_pose_estimation/README.md b/PaddleCV/human_pose_estimation/README.md
index c563ce31b6a7d84de85b3d41f70a153f3e4fb7b7..8e7b6c1342f8fcc022ec46ca40f02507abb87582 100644
--- a/PaddleCV/human_pose_estimation/README.md
+++ b/PaddleCV/human_pose_estimation/README.md
@@ -91,7 +91,7 @@ python val.py --dataset 'mpii' --checkpoint 'checkpoints/pose-resnet50-mpii-384x
 ### Perform Training
 
 ```bash
-python train.py --dataset 'mpii' --data_root 'data/mpii'
+python train.py --dataset 'mpii' # or coco
 ```
 
 **Note**: Configurations for training are aggregated in the `lib/mpii_reader.py` and `lib/coco_reader.py`.
diff --git a/PaddleCV/human_pose_estimation/README_cn.md b/PaddleCV/human_pose_estimation/README_cn.md
index 86f71aa580c96789f73e87917921ea3456f03241..b5ef692c4d89bffe269b019caaee97d4dc49d877 100644
--- a/PaddleCV/human_pose_estimation/README_cn.md
+++ b/PaddleCV/human_pose_estimation/README_cn.md
@@ -89,7 +89,7 @@ python val.py --dataset 'mpii' --checkpoint 'checkpoints/pose-resnet50-mpii-384x
 ### 模型训练
 
 ```bash
-python train.py --dataset 'mpii' --data_root 'data/mpii'
+python train.py --dataset 'mpii'
 ```
 
 **说明** 详细参数配置已保存到`lib/mpii_reader.py` 和 `lib/coco_reader.py`文件中，通过设置dataset来选择使用具体的参数配置
diff --git a/PaddleCV/human_pose_estimation/utils/utility.py b/PaddleCV/human_pose_estimation/utils/utility.py
index 9c3cd61fbbd41ea2262802beb548d80f13fd1a38..698d0231b8230bb367f5455ce7bab690d911c03b 100644
--- a/PaddleCV/human_pose_estimation/utils/utility.py
+++ b/PaddleCV/human_pose_estimation/utils/utility.py
@@ -41,7 +41,7 @@ def print_arguments(args):
     :type args: argparse.Namespace
     """
     print("-----------  Configuration Arguments -----------")
-    for arg, value in sorted(vars(args).iteritems()):
+    for arg, value in sorted(vars(args).items()):
         print("%s: %s" % (arg, value))
     print("------------------------------------------------")