diff --git a/model_zoo/official/cv/tinydarknet/README.md b/model_zoo/official/cv/tinydarknet/README.md
index fbac7f4354..d3153fe2a9 100644
--- a/model_zoo/official/cv/tinydarknet/README.md
+++ b/model_zoo/official/cv/tinydarknet/README.md
@@ -71,7 +71,7 @@ After installing MindSpore via the official website, you can start training and
 
   ```python
   # run training example
-  bash ./scripts/run_standalone_train.sh
+  bash ./scripts/run_standalone_train.sh 0
 
   # run distributed training example
   bash ./scripts/run_distribute_train.sh rank_table.json
@@ -164,7 +164,7 @@ For more configuration details, please refer the script config.py.
 - running on Ascend：
 
   ```python
-  bash scripts/run_standalone_train.sh
+  bash scripts/run_standalone_train.sh 0
   ```
 
   The command above will run in the background, you can view the results through the file train.log.
diff --git a/model_zoo/official/cv/tinydarknet/README_CN.md b/model_zoo/official/cv/tinydarknet/README_CN.md
index 890b9b4b87..5309f323f7 100644
--- a/model_zoo/official/cv/tinydarknet/README_CN.md
+++ b/model_zoo/official/cv/tinydarknet/README_CN.md
@@ -79,7 +79,7 @@ Tiny-DarkNet是Joseph Chet Redmon等人提出的一个16层的针对于经典的
 
   ```python
   # 单卡训练
-  bash ./scripts/run_standalone_train.sh
+  bash ./scripts/run_standalone_train.sh 0
 
   # 分布式训练
   bash ./scripts/run_distribute_train.sh rank_table.json
@@ -172,7 +172,7 @@ Tiny-DarkNet是Joseph Chet Redmon等人提出的一个16层的针对于经典的
 - 在Ascend资源上运行：
 
   ```python
-  bash ./scripts/run_standalone_train.sh
+  bash ./scripts/run_standalone_train.sh 0
   ```
 
   上述的命令将运行在后台中，可以通过 `train.log` 文件查看运行结果.
diff --git a/model_zoo/official/cv/tinydarknet/scripts/run_standalone_train.sh b/model_zoo/official/cv/tinydarknet/scripts/run_standalone_train.sh
index a72be567fb..d91521ce48 100644
--- a/model_zoo/official/cv/tinydarknet/scripts/run_standalone_train.sh
+++ b/model_zoo/official/cv/tinydarknet/scripts/run_standalone_train.sh
@@ -14,9 +14,10 @@
 # limitations under the License.
 # ============================================================================
 
+export DEVICE_ID=$1
 rm -rf ./train_single
 mkdir ./train_single
 cp -r ./src ./train_single
 cp ./train.py ./train_single
 cd ./train_single
-python ./train.py > ./train.log 2>&1 &
+python ./train.py --device_id=$DEVICE_ID > ./train.log 2>&1 &