diff --git a/docs/get_started/model_optimization.md b/docs/get_started/model_optimization.md
index dfd1b93c02a489d9fd492bb1eff8e846f665d2d3..4519680a9710e12ac991a94b9ae4eebee1ef67bd 100644
--- a/docs/get_started/model_optimization.md
+++ b/docs/get_started/model_optimization.md
@@ -168,6 +168,7 @@ mmsegmentation==0.30.0
 ninja
 ```
 通过pip install -r requirements.txt进行安装。
+
 2. mmcv三方库安装，目前1.7.2版本支持npu，需要手动下载代码，进行源码编译安装：
 ```python
 git clone -b 1.x https://github.com/open-mmlab/mmcv.git
diff --git a/model_examples/CenterPoint/README.md b/model_examples/CenterPoint/README.md
index 2c7e1f1af219eaf2d046db56d6b6604877ce477e..66f81b18d1dede341a7206ed9ef741d03dcaad5b 100644
--- a/model_examples/CenterPoint/README.md
+++ b/model_examples/CenterPoint/README.md
@@ -140,21 +140,7 @@ python -c "import cumm"
     python -c "import spconv"
     ```
 
-#### 2.4 编译安装pytorch-scatter
-执行以下命令编译安装pytorch-scatter
-```shell
-git clone https://github.com/rusty1s/pytorch_scatter.git -b 2.1.1
-cd ./pytorch_scatter/
-python setup.py bdist_wheel
-cd ../ && pip install pytorch_scatter/dist/torch_scatter-*.whl
-```
-
-【注意】安装完毕后建议运行以下命令，如无报错，证明安装无误，可继续安装流程
-```shell
-python -c "import torch_scatter"
-```
-
-#### 2.5 编译安装Driving SDK
+#### 2.4 编译安装Driving SDK
 参考Driving SDK官方gitee仓README安装编译构建并安装Driving SDK包：[参考链接](https://gitee.com/ascend/DrivingSDK)
 
 【注意】安装完毕后建议运行以下命令，如无报错，证明安装无误，可继续安装流程
@@ -162,7 +148,7 @@ python -c "import torch_scatter"
 python -c "import mx_driving"
 ```
 
-#### 2.6 编译安装OpenPCDet
+#### 2.5 编译安装OpenPCDet
 执行以下命令，应用过patch的模型根目录编译安装OpenPCDet
 ```shell
 cd ./OpenPCDet/
@@ -328,7 +314,7 @@ python -c "import cumm"
     python -c "import spconv"
     ```
 
-#### 2.5 编译安装Driving SDK
+#### 2.4 编译安装Driving SDK
 参考Driving SDK官方gitee仓README安装编译构建并安装Driving SDK包：[参考链接](https://gitee.com/ascend/DrivingSDK)
 
 【注意】安装完毕后建议运行以下命令，如无报错，证明安装无误，可继续安装流程
@@ -336,14 +322,14 @@ python -c "import cumm"
 python -c "import mx_driving"
 ```
 
-#### 2.6 编译安装OpenPCDet
+#### 2.5 编译安装OpenPCDet
 在应用过patch文件模型根目录，执行以下命令，编译安装OpenPCDet
 ```shell
 cd ./OpenPCDet/
 python setup.py develop
 ```
 
-#### 2.7 高性能内存库替换
+#### 2.6 高性能内存库替换
 参考昇腾官方指导文档，下载高性能内存库并导入环境变量[参考链接](https://www.hiascend.com/document/detail/zh/Pytorch/600/ptmoddevg/trainingmigrguide/performance_tuning_0067.html)
 
 ### 准备数据集
diff --git a/model_examples/CenterPoint/test/train_centerpoint3d_full_8p.sh b/model_examples/CenterPoint/test/train_centerpoint3d_full_8p.sh
index 3f0d020e23a25116c55a33de455b624fa51ce156..2c9cd5fbb2f4673341a3f5e5c6fbc967192f7b56 100644
--- a/model_examples/CenterPoint/test/train_centerpoint3d_full_8p.sh
+++ b/model_examples/CenterPoint/test/train_centerpoint3d_full_8p.sh
@@ -73,7 +73,7 @@ nohup python -m torch.distributed.launch \
           train.py \
           --launcher pytorch \
           --cfg_file ${cfg_file} \
-          --logger_iter_interva 1  > ${test_path_dir}/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log 2>&1 &
+          --logger_iter_interval 1  > ${test_path_dir}/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log 2>&1 &
 wait
 
 #训练结束时间，不需要修改
diff --git a/model_examples/CenterPoint/test/train_centerpoint3d_performance_8p.sh b/model_examples/CenterPoint/test/train_centerpoint3d_performance_8p.sh
index 8f85cca6b8fcfb91bf7bc9ffd9ecca6a24f68181..8708c004b1633ff48030d15a0f86928a1f2d4ed2 100644
--- a/model_examples/CenterPoint/test/train_centerpoint3d_performance_8p.sh
+++ b/model_examples/CenterPoint/test/train_centerpoint3d_performance_8p.sh
@@ -74,7 +74,7 @@ nohup python -m torch.distributed.launch \
           --launcher pytorch \
           --cfg_file ${cfg_file} \
           --epochs 1 \
-          --logger_iter_interva 1 > ${test_path_dir}/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log 2>&1 &
+          --logger_iter_interval 1 > ${test_path_dir}/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log 2>&1 &
 wait
 
 #训练结束时间，不需要修改
diff --git a/model_examples/PointPillar/test/train_pointpillar_performance_8p.sh b/model_examples/PointPillar/test/train_pointpillar_performance_8p.sh
index 1feceddacb9eb86212b4a9b78a28a8385a488256..12e727e30100ec284956088c40e9ffbde0308264 100644
--- a/model_examples/PointPillar/test/train_pointpillar_performance_8p.sh
+++ b/model_examples/PointPillar/test/train_pointpillar_performance_8p.sh
@@ -70,7 +70,9 @@ nohup python -m torch.distributed.launch \
           --rdzv_endpoint=localhost:${PORT} \
           train.py \
           --launcher pytorch \
-          --cfg_file ${cfg_file}  > ${test_path_dir}/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log 2>&1 &
+          --cfg_file ${cfg_file} \
+          --epochs 1 \
+          --logger_iter_interval 1 > ${test_path_dir}/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log 2>&1 &
 wait
 
 #训练结束时间，不需要修改