diff --git a/PaddleCV/PaddleDetection/docs/GETTING_STARTED.md b/PaddleCV/PaddleDetection/docs/GETTING_STARTED.md
index a74d5ebf18a6f40e5304efc5c7567c92fe190ca6..c0b11d96f74782d70b9ea44a9b0111aca547a17c 100644
--- a/PaddleCV/PaddleDetection/docs/GETTING_STARTED.md
+++ b/PaddleCV/PaddleDetection/docs/GETTING_STARTED.md
@@ -37,7 +37,7 @@ python tools/train.py -c configs/faster_rcnn_r50_1x.yml -o use_gpu=false
 - `--eval`: Whether to perform evaluation in training, default is `False`
 - `--output_eval`: If perform evaluation in training, this edits evaluation directory, default is current directory.
 - `-d` or `--dataset_dir`: Dataset path, same as `dataset_dir` of configs. Such as: `-d dataset/coco`
-- `-o`: Set configuration options in config file. Such as: `-o weights=output/faster_rcnn_r50_1x/model_final`
+- `-o`: Set configuration options in config file. Such as: `-o max_iters=180000`
 
 
 ##### Examples
@@ -60,7 +60,6 @@ the best model with highest MAP is saved at each `snapshot_iter`. `best_model` h
 export CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
 export PYTHONPATH=$PYTHONPATH:.
 python -u tools/train.py -c configs/faster_rcnn_r50_1x.yml \
-                         -o weights=output/faster_rcnn_r50_1x/model_final \
                          -d dataset/coco
 ```
 
diff --git a/PaddleCV/PaddleDetection/docs/GETTING_STARTED_cn.md b/PaddleCV/PaddleDetection/docs/GETTING_STARTED_cn.md
index de7f8833d2f9b57dee28df27251a07e8064d9e9f..2150123e94be4f7c8123b255e5a00ab1436184ae 100644
--- a/PaddleCV/PaddleDetection/docs/GETTING_STARTED_cn.md
+++ b/PaddleCV/PaddleDetection/docs/GETTING_STARTED_cn.md
@@ -38,7 +38,7 @@ python tools/train.py -c configs/faster_rcnn_r50_1x.yml -o use_gpu=false
 - `--eval`: 是否边训练边测试，默认是 `False`
 - `--output_eval`: 如果边训练边测试, 这个参数可以编辑评测保存json路径, 默认是当前目录。
 - `-d` or `--dataset_dir`: 数据集路径, 同配置文件里的`dataset_dir`. 例如: `-d dataset/coco`
-- `-o`: 设置配置文件里的参数内容。 例如: `-o weights=output/faster_rcnn_r50_1x/model_final`
+- `-o`: 设置配置文件里的参数内容。 例如: `-o max_iters=180000`
 
 ##### 例子
 
@@ -57,7 +57,6 @@ python -u tools/train.py -c configs/faster_rcnn_r50_1x.yml --eval
 export CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
 export PYTHONPATH=$PYTHONPATH:.
 python -u tools/train.py -c configs/faster_rcnn_r50_1x.yml \
-                         -o weights=output/faster_rcnn_r50_1x/model_final \
                          -d dataset/coco
 ```