diff --git a/fluid/recommendation/gru4rec/README.md b/fluid/recommendation/gru4rec/README.md
index 81137405052f08a625ed73e35d30846330c86e7e..d4489bfbbfb92f15a43d0384bf24b353d107c6fc 100644
--- a/fluid/recommendation/gru4rec/README.md
+++ b/fluid/recommendation/gru4rec/README.md
@@ -74,17 +74,16 @@ python convert_format.py
 ```
 
 ## 训练
---use_cuda 表示使用gpu --parallel 表示多卡
+'--use_cuda 1' 表示使用gpu --parallel 1 表示多卡
 
 GPU 环境
-运行命令 `CUDA_VISIBLE_DEVICES=0 python train.py train_file test_file --use_cuda` 开始训练模型。
-
-```python
-CUDA_VISIBLE_DEVICES=0 python train.py small_train.txt small_test.txt --use_cuda
+运行命令 `CUDA_VISIBLE_DEVICES=0 python train.py train_file test_file --use_cuda 1` 开始训练模型。
+```
+CUDA_VISIBLE_DEVICES=0 python train.py small_train.txt small_test.txt --use_cuda 1
 ```
 CPU 环境
 运行命令 `python train.py train_file test_file` 开始训练模型。
-```python
+```
 python train.py small_train.txt small_test.txt
 ```
 
diff --git a/fluid/recommendation/gru4rec/train.py b/fluid/recommendation/gru4rec/train.py
index 5474c82800373e52dc4a4537ea978972c0d4edbb..12bc1bc20ed93e1376e97ef4c8e76af51a529cc8 100644
--- a/fluid/recommendation/gru4rec/train.py
+++ b/fluid/recommendation/gru4rec/train.py
@@ -185,6 +185,7 @@ def train_net():
     test_file = args.test_file
     use_cuda = True if args.use_cuda else False
     parallel = True if args.parallel else False
+    print("use_cuda:", use_cuda, "parallel:", parallel)
     batch_size = 50
     vocab, train_reader, test_reader = utils.prepare_data(
         train_file, test_file,batch_size=batch_size * get_cards(args),\