diff --git a/official/cv/tinydarknet/README.md b/official/cv/tinydarknet/README.md
index 2bdca4270d4a37f3296d26f095eabd55b2fc9a1b..c5aba2f4e2b6cc5c0e401b0d15ea5e3d4813685c 100644
--- a/official/cv/tinydarknet/README.md
+++ b/official/cv/tinydarknet/README.md
@@ -75,16 +75,17 @@ After installing MindSpore via the official website, you can start training and
 - running on Ascend:
 
   ```python
-  # run training example
-  bash ./scripts/run_standalone_train.sh 0
+  # run in standalone environment
+  cd scripts/
+  bash run_standalone_train.sh [DEVICE_ID] [TRAIN_DATA_DIR] [cifar10|imagenet]
 
-  # run distributed training example
-  bash ./scripts/run_distribute_train.sh /{path}/*.json
+  # run in distribute environment
+  cd scripts/
+  bash run_distribute_train.sh [RANK_TABLE_FILE] [cifar10|imagenet] [TRAIN_DATA_DIR]
 
-  # run evaluation example
-  python eval.py > eval.log 2>&1 &
-  OR
-  bash ./script/run_eval.sh
+  # evaluation
+  cd scripts/
+  bash run_train.sh [VAL_DATA_DIR] [cifar10|imagenet] [checkpoint_path]
   ```
 
   For distributed training, a hccl configuration file [RANK_TABLE_FILE] with JSON format needs to be created in advance.
@@ -98,11 +99,11 @@ After installing MindSpore via the official website, you can start training and
   ```python
   # GPU standalone training example
   python train.py  \
-  --config_path=./imagenet_config_gpu.yaml \
+  --config_path=./config/imagenet_config_gpu.yaml \
   --dataset_name=imagenet --train_data_dir=../dataset/imagenet_original/train --device_target=GPU
-  OR
-  cd scripts
-  bash run_distribute_train_gpu.sh [DEVICE_ID] [TRAIN_DATA_DIR] [cifar10 | imagenet]
+  # OR
+  cd scripts/
+  bash run_standalone_train_gpu.sh [DEVICE_ID] [TRAIN_DATA_DIR] [cifar10|imagenet]
 
   # GPU distribute training example
   export RANK_SIZE=8
@@ -112,14 +113,15 @@ After installing MindSpore via the official website, you can start training and
   --dataset_name=imagenet \
   --train_data_dir=../dataset/imagenet_original/train \
   --device_target=GPU
-  OR
-  bash scripts/run_distribute_train_gpu.sh [RANK_SIZE] [TRAIN_DATA_DIR] [cifar10 | imagenet]
+  # OR
+  cd scripts/
+  bash run_distribute_train_gpu.sh [RANK_SIZE] [TRAIN_DATA_DIR] [cifar10|imagenet]
 
   # GPU evaluation example
   python eval.py -device_target=GPU --val_data_dir=../dataset/imagenet_original/val --dataset_name=imagenet --config_path=./config/imagenet_config_gpu.yaml \
   --checkpoint_path=$PATH2
-  OR
-  bash scripts/run_train_gpu.sh [VAL_DATA_DIR] [cifar10|imagenet] [checkpoint_path]
+  # OR
+  bash run_eval_gpu.sh [VAL_DATA_DIR] [cifar10|imagenet] [checkpoint_path]
   ```
 
 - Running on ModelArts
@@ -265,7 +267,8 @@ For more configuration details, please refer the script `imagenet_config.yaml`.
 - running on Ascend:
 
   ```python
-  bash ./scripts/run_standalone_train.sh [DEVICE_ID]
+  cd scripts/
+  bash run_standalone_train.sh [DEVICE_ID] [TRAIN_DATA_DIR] [cifar10|imagenet]
   ```
 
   The command above will run in the background, you can view the results through the file train.log.
@@ -290,7 +293,7 @@ For more configuration details, please refer the script `imagenet_config.yaml`.
 - running on GPU:
 
   ```python
-  cd scripts
+  cd scripts/
   bash run_standalone_train_gpu.sh [DEVICE_ID] [TRAIN_DATA_DIR] [cifar10|imagenet]
   ```
 
@@ -313,7 +316,8 @@ For more configuration details, please refer the script `imagenet_config.yaml`.
 - running on CPU
 
   ```python
-  bash scripts/run_train_cpu.sh [TRAIN_DATA_DIR] [cifar10|imagenet]
+  cd scripts/
+  bash run_train_cpu.sh [TRAIN_DATA_DIR] [cifar10|imagenet]
   ```
 
 ### [Distributed Training](#contents)
@@ -321,7 +325,8 @@ For more configuration details, please refer the script `imagenet_config.yaml`.
 - running on Ascend:
 
   ```python
-  bash ./scripts/run_distribute_train.sh [RANK_TABLE_FILE]
+  cd scripts/
+  bash run_distribute_train.sh [RANK_TABLE_FILE] [cifar10|imagenet] [TRAIN_DATA_DIR]
   ```
 
   The above shell script will run distribute training in the background. You can view the results through the file train_parallel[X]/log. The loss value will be achieved as follows:
@@ -340,7 +345,8 @@ For more configuration details, please refer the script `imagenet_config.yaml`.
 - running on GPU:
 
   ```python
-  bash scripts/run_distribute_train_gpu.sh [RANK_SIZE] [TRAIN_DATA_DIR] [cifar10|imagenet]
+  cd scripts/
+  bash run_standalone_train_gpu.sh [DEVICE_ID] [TRAIN_DATA_DIR] [cifar10|imagenet]
   ```
 
   The above shell script will run distribute training in the background. You can view the results through the file train_parallel[X]/log. The loss value will be achieved as follows:
@@ -365,9 +371,9 @@ For more configuration details, please refer the script `imagenet_config.yaml`.
   Before running the command below, please check the checkpoint path used for evaluation. Please set the checkpoint path to be the absolute full path, e.g., "/username/tinydaeknet/train_tinydarknet.ckpt".
 
   ```python
-  python eval.py > eval.log 2>&1 &  
-  OR
-  bash scripts/run_eval.sh
+  python eval.py  --val_data_dir=VAL_DATA_PATH --dataset_name=cifar10|imagenet --config_path=CONFIG_FILE --checkpoint_path=CHECKPOINT_PATH
+  # OR
+  bash run_eval.sh [VAL_DATA_DIR] [cifar10|imagenet] [checkpoint_path]
   ```
 
   The above python command will run in the background. You can view the results through the file "eval.log". The accuracy of the test dataset will be as follows:
@@ -389,7 +395,7 @@ For more configuration details, please refer the script `imagenet_config.yaml`.
   Before running the command below, please check the checkpoint path used for evaluation. Please set the checkpoint path to be the absolute full path, e.g., "/username/tinydaeknet/train_tinydarknet.ckpt".
 
   ```python
-  bash scripts/run_train_gpu.sh [VAL_DATA_DIR] [cifar10|imagenet] [checkpoint_path]
+  bash run_eval_gpu.sh [VAL_DATA_DIR] [cifar10|imagenet] [checkpoint_path]
   ```
 
   The above python command will run in the background. You can view the results through the file "eval.log". The accuracy of the test dataset will be as follows:
@@ -411,7 +417,7 @@ For more configuration details, please refer the script `imagenet_config.yaml`.
   Before running the command below, please check the checkpoint path used for evaluation. Please set the checkpoint path to be the absolute full path, e.g., "/username/tinydaeknet/train_tinydarknet.ckpt".
 
   ```python
-  bash scripts/run_eval.sh [VAL_DATA_DIR] [imagenet|cifar10] [CHECKPOINT_PATH]
+  bash run_eval_cpu.sh [VAL_DATA_DIR] [cifar10|imagenet] [checkpoint_path]
   ```
 
   You can view the results through the file "eval.log". The accuracy of the test dataset will be as follows:
@@ -429,7 +435,7 @@ For more configuration details, please refer the script `imagenet_config.yaml`.
 
 ```shell
 # Ascend310 inference
-python export.py --dataset [DATASET] --file_name [FILE_NAME] --file_format [EXPORT_FORMAT]
+python export.py --dataset_name [DATASET] --file_name [FILE_NAME] --file_format [EXPORT_FORMAT]
 ```
 
 - Export on ModelArts (If you want to run in modelarts, please check the official documentation of [modelarts](https://support.huaweicloud.com/modelarts/), and you can start as follows)
@@ -488,33 +494,33 @@ Inference result is saved in current path, you can find result like this in acc.
 
 ### [Training Performance](#contents)
 
-| Parameters                        | Ascend                                                      | GPU                                                 |
-| -------------------------- | ------------------------------------------------------------| ----------------------------------------------------|
-| Model Version                   | V1                                                          | V1                                                  |
-| Resource                        | Ascend 910;CPU 2.60GHz,56cores;内存 314G;系统 Euler2.8  | PCIE V100-32G                                    |
-| Uploaded Date                   | 2020/12/22                                                  | 2021/07/15                         |
-| MindSpore Version              | 1.1.0                                                       | 1.3.0                                               |
-| Dataset                     | 1200k images                                               | 1200k images                           |
-| Training Parameters                   | epoch=500, steps=1251, batch_size=128, lr=0.1               | epoch=500, steps=1251, batch_size = 128, lr=0.005   |
-| Optimizer                     | Momentum                                                    | Momentum                                            |
-| Loss Function                   | Softmax Cross Entropy                                       | Softmax Cross Entropy                               |
-| Speed                       | 8pc: 104 ms/step                                            | 8pc: 255 ms/step                                          |
-| Parameters(M)                    | 4.0;                                                        | 4.0;                               |
+| Parameters                        | Ascend                                                      | GPU                                                 |                       CPU                        |
+| -------------------------- | ------------------------------------------------------------| ----------------------------------------------------|------------------------------------------------|
+| Model Version                   | V1                                                          | V1                                                  |                       V1                      |
+| Resource                        | Ascend 910;CPU 2.60GHz,56cores;内存 314G;系统 Euler2.8  | PCIE V100-32G                                    |                     CPU 72cores, Memory 503G               |
+| Uploaded Date                   | 2020/12/22                                                  | 2021/07/15                         |                        2021/12/22                   |
+| MindSpore Version              | 1.1.0                                                       | 1.3.0                                               |                        1.5.0                 |
+| Dataset                     | 1200k images                                               | 1200k images                           |                       1200k图片                        |
+| Training Parameters                   | epoch=500, steps=1251, batch_size=128, lr=0.1               | epoch=500, steps=1251, batch_size = 128, lr=0.005   |            epoch=500, steps=10009, batch_size=128, lr=0.1                |
+| Optimizer                     | Momentum                                                    | Momentum                                            |                      Momentum                   |
+| Loss Function                   | Softmax Cross Entropy                                       | Softmax Cross Entropy                               |                   Softmax Cross Entropy                  |
+| Speed                       | 8pc: 104 ms/step                                            | 8pc: 255 ms/step                                          |                          1p:11081 ms/step                     |
+| Parameters(M)                    | 4.0;                                                        | 4.0;                               |                             4.0;                       |
 | Scripts                       | [Tiny-Darknet scripts](https://gitee.com/mindspore/models/tree/master/official/cv/tinydarknet)
 
 ### [Evaluation Performance](#contents)
 
-| Parameters                 | Ascend                            | GPU                               |
-| ------------------- | ----------------------------------| ----------------------------------|
-| Model Version             | V1                                | V1                                |
-| Resource                |  Ascend 910;Euler2.8        | PCIE V100-32G                  |
-| Uploaded Date            | 2020/12/22                        | 2021/7/15                         |
-| MindSpore Version       | 1.1.0                             | 1.3.0                             |
-| Dataset              | 200k images                        | 200k images                        |
-| batch_size          | 128                               | 128                               |
-| Outputs                | probability                          | probability                          |
-| Accuracy              | 8pcs Top-1: 58.7%; Top-5: 81.7%    | 8pcs Top-1: 58.9%; Top-5: 81.7%    |
-| Model for inference            | 11.6M (.ckpt file)                 | 10.06M (.ckpt file)                |
+| Parameters          | Ascend                            | GPU                               |                              |
+| ------------------- | ----------------------------------| ----------------------------------|------------------------------|
+| Model Version       | V1                                | V1                                | V1                           |
+| Resource            |  Ascend 910; Euler2.8             | PCIE V100-32G                     | CPU 72cores, Memory 503G     |
+| Uploaded Date       | 2020/12/22                        | 2021/7/15                         | 2020/12/22                   |
+| MindSpore Version   | 1.1.0                             | 1.3.0                             | 1.5.0                        |
+| Dataset             | 200k images                       | 200k images                       | 200k images                  |
+| batch_size          | 128                               | 128                               | 128                          |
+| Outputs             | probability                       | probability                       | probability                  |
+| Accuracy            | 8pcs Top-1: 58.7%; Top-5: 81.7%   | 8pcs Top-1: 58.9%; Top-5: 81.7%   | 1p: Top-1: 58.7%; Top-5:81.5 |
+| Model for inference | 11.6M (.ckpt file)                | 10.06M (.ckpt file)               | 11.6M (.ckpt file)           |
 
 ### [Inference Performance](#contents)
 
diff --git a/official/cv/tinydarknet/README_CN.md b/official/cv/tinydarknet/README_CN.md
index 2942d0c59328c412e0626517990f9f121de28649..655033c76240580e1409557464e415596a131571 100644
--- a/official/cv/tinydarknet/README_CN.md
+++ b/official/cv/tinydarknet/README_CN.md
@@ -84,15 +84,16 @@ 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 0
+  cd scripts/
+  bash run_standalone_train.sh [DEVICE_ID] [TRAIN_DATA_DIR] [cifar10|imagenet]
 
   # 分布式训练
-  bash ./scripts/run_distribute_train.sh /{path}/*.json
+  cd scripts/
+  bash run_distribute_train.sh [RANK_TABLE_FILE] [cifar10|imagenet] [TRAIN_DATA_DIR]
 
   # 评估
-  python eval.py > eval.log 2>&1 &
-  OR
-  bash ./script/run_eval.sh
+  cd scripts/
+  bash run_train.sh [VAL_DATA_DIR] [cifar10|imagenet] [checkpoint_path]
   ```
 
   进行并行训练时, 需要提前创建JSON格式的hccl配置文件 [RANK_TABLE_FILE]。
@@ -108,9 +109,9 @@ Tiny-DarkNet是Joseph Chet Redmon等人提出的一个16层的针对于经典的
   python train.py  \
   --config_path=./config/imagenet_config_gpu.yaml \
   --dataset_name=imagenet --train_data_dir=../dataset/imagenet_original/train --device_target=GPU
-  OR
-  cd scripts
-  bash run_distribute_train_gpu.sh [DEVICE_ID] [TRAIN_DATA_DIR] [cifar10 | imagenet]
+  # OR
+  cd scripts/
+  bash run_standalone_train_gpu.sh [DEVICE_ID] [TRAIN_DATA_DIR] [cifar10|imagenet]
 
   # GPU多卡训练示例
   export RANK_SIZE=8
@@ -120,14 +121,15 @@ Tiny-DarkNet是Joseph Chet Redmon等人提出的一个16层的针对于经典的
   --dataset_name=imagenet \
   --train_data_dir=../dataset/imagenet_original/train \
   --device_target=GPU
-  OR
-  bash scripts/run_distribute_train_gpu.sh [RANK_SIZE] [TRAIN_DATA_DIR] [cifar10 | imagenet]
+  # OR
+  cd scripts/
+  bash run_distribute_train_gpu.sh [RANK_SIZE] [TRAIN_DATA_DIR] [cifar10|imagenet]
 
   # GPU评估示例
   python eval.py -device_target=GPU --val_data_dir=../dataset/imagenet_original/val --dataset_name=imagenet --config_path=./config/imagenet_config_gpu.yaml \
   --checkpoint_path=$PATH2
-  OR
-  bash scripts/run_train_gpu.sh [VAL_DATA_DIR] [cifar10|imagenet] [checkpoint_path]
+  # OR
+  bash run_eval_gpu.sh [VAL_DATA_DIR] [cifar10|imagenet] [checkpoint_path]
   ```
 
 - 在ModelArts上运行
@@ -272,7 +274,8 @@ 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 [DEVICE_ID]
+  cd scripts/
+  bash run_standalone_train.sh [DEVICE_ID] [TRAIN_DATA_DIR] [cifar10|imagenet]
   ```
 
   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.
@@ -297,7 +300,7 @@ Tiny-DarkNet是Joseph Chet Redmon等人提出的一个16层的针对于经典的
 - 在GPU资源上运行:
 
   ```python
-  cd scripts
+  cd scripts/
   bash run_standalone_train_gpu.sh [DEVICE_ID] [TRAIN_DATA_DIR] [cifar10|imagenet]
   ```
 
@@ -320,7 +323,8 @@ Tiny-DarkNet是Joseph Chet Redmon等人提出的一个16层的针对于经典的
 - 在CPU资源上运行:
 
   ```python
-  bash scripts/run_train_cpu.sh [TRAIN_DATA_DIR] [cifar10|imagenet]
+  cd scripts/
+  bash run_train_cpu.sh [TRAIN_DATA_DIR] [cifar10|imagenet]
   ```
 
 ### [分布式训练](#目录)
@@ -328,7 +332,8 @@ 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_distribute_train.sh [RANK_TABLE_FILE]
+  cd scripts/
+  bash run_distribute_train.sh [RANK_TABLE_FILE] [cifar10|imagenet] [TRAIN_DATA_DIR]
   ```
 
   上述的脚本命令将在后台中进行分布式训练,可以通过`distribute_train/nohup.out`文件查看运行结果. 训练的损失值将以如下的形式展示:
@@ -347,7 +352,8 @@ Tiny-DarkNet是Joseph Chet Redmon等人提出的一个16层的针对于经典的
 - 在GPU资源上运行:
 
   ```python
-  bash scripts/run_distribute_train_gpu.sh [RANK_SIZE] [TRAIN_DATA_DIR] [cifar10|imagenet]
+  cd scripts/
+  bash run_standalone_train_gpu.sh [DEVICE_ID] [TRAIN_DATA_DIR] [cifar10|imagenet]
   ```
 
   上述的脚本命令将在后台中进行分布式训练,可以通过`distribute_train_gpu/nohup.out`文件查看运行结果. 训练的损失值将以如下的形式展示:
@@ -372,9 +378,9 @@ Tiny-DarkNet是Joseph Chet Redmon等人提出的一个16层的针对于经典的
   在运行如下命令前,请确认用于评估的checkpoint文件的路径.checkpoint文件须包含在tinydarknet文件夹内.请将checkpoint路径设置为相对于 eval.py文件 的路径,例如:"./ckpts/train_tinydarknet.ckpt"(ckpts 与 eval.py 同级).
 
   ```python
-  python eval.py > eval.log 2>&1 &  
-  OR
-  bash scripts/run_eval.sh
+  python eval.py  --val_data_dir=VAL_DATA_PATH --dataset_name=cifar10|imagenet --config_path=CONFIG_FILE --checkpoint_path=CHECKPOINT_PATH
+  # OR
+  bash run_eval.sh [VAL_DATA_DIR] [cifar10|imagenet] [checkpoint_path]
   ```
 
   上述的python命令将运行在后台中,可以通过"eval.log"文件查看结果. 测试数据集的准确率将如下面所列:
@@ -396,7 +402,7 @@ Tiny-DarkNet是Joseph Chet Redmon等人提出的一个16层的针对于经典的
   在运行如下命令前,请确认用于评估的checkpoint文件的路径.checkpoint文件须包含在tinydarknet文件夹内.请将checkpoint路径设置为相对于 eval.py文件 的路径,例如:"./ckpts/train_tinydarknet.ckpt"(ckpts 与 eval.py 同级).
 
   ```python
-  bash scripts/run_train_gpu.sh [VAL_DATA_DIR] [cifar10|imagenet] [checkpoint_path]
+  bash run_eval_gpu.sh [VAL_DATA_DIR] [cifar10|imagenet] [checkpoint_path]
   ```
 
   上述的python命令将运行在后台中,可以通过"eval.log"文件查看结果. 测试数据集的准确率将如下面所列:
@@ -418,7 +424,7 @@ Tiny-DarkNet是Joseph Chet Redmon等人提出的一个16层的针对于经典的
   在运行如下命令前,请确认用于评估的checkpoint文件的路径.checkpoint文件须包含在tinydarknet文件夹内.请将checkpoint路径设置为相对于 eval.py文件 的路径,例如:"./ckpts/train_tinydarknet.ckpt"(ckpts 与 eval.py 同级).
 
   ```python
-  bash scripts/run_eval_cpu.sh [VAL_DATA_DIR] [imagenet|cifar10] [CHECKPOINT_PATH]
+  bash run_eval_cpu.sh [VAL_DATA_DIR] [cifar10|imagenet] [checkpoint_path]
   ```
 
   可以通过"eval.log"文件查看结果. 测试数据集的准确率将如下面所列:
@@ -435,7 +441,7 @@ Tiny-DarkNet是Joseph Chet Redmon等人提出的一个16层的针对于经典的
 - 在本地导出
 
 ```shell
-python export.py --dataset [DATASET] --file_name [FILE_NAME] --file_format [EXPORT_FORMAT]
+python export.py --dataset_name [DATASET] --file_name [FILE_NAME] --file_format [EXPORT_FORMAT]
 ```
 
 - 在ModelArts上导出
@@ -496,34 +502,34 @@ bash run_infer_310.sh [MINDIR_PATH] [DATA_PATH] [LABEL_PATH] [DVPP] [DEVICE_ID]
 
 #### Tinydarknet on ImageNet 2012
 
-| 参数                       | Ascend                                                      | GPU                                                 |
-| -------------------------- | ------------------------------------------------------------| ----------------------------------------------------|
-| 模型版本                   | V1                                                          | V1                                                  |
-| 资源                       | Ascend 910;CPU 2.60GHz,56cores;内存 314G;系统 Euler2.8  | PCIE V100-32G                                       |
-| 上传日期                   | 2020/12/22                                                  | 2021/07/15                                          |
-| MindSpore版本              | 1.1.0                                                       | 1.3.0                                               |
-| 数据集                     | 1200k张图片                                                 | 1200k张图片                                         |
-| 训练参数                   | epoch=500, steps=1251, batch_size=128, lr=0.1               | epoch=500, steps=1251, batch_size = 128, lr=0.005   |
-| 优化器                     | Momentum                                                    | Momentum                                            |
-| 损失函数                   | Softmax Cross Entropy                                       | Softmax Cross Entropy                               |
-| 速度                       | 8卡: 104 ms/step                                            | 8卡: 255 ms/step                                    |
-| 总时间                     | 8卡: 17.8小时                                               | 8卡: 46.9小时                                       |
-| 参数(M)                    | 4.0;                                                        | 4.0;                                              |
+| 参数                       | Ascend                                                      | GPU                                                 |                       CPU                        |
+| -------------------------- | ------------------------------------------------------------| ----------------------------------------------------|------------------------------------------------|
+| 模型版本                   | V1                                                          | V1                                                  |                       V1                      |
+| 资源                       | Ascend 910;CPU 2.60GHz,56cores;内存 314G;系统 Euler2.8  | PCIE V100-32G                                       |                     CPU 72cores, 内存 503G               |
+| 上传日期                   | 2020/12/22                                                  | 2021/07/15                                          |                        2021/12/22                   |
+| MindSpore版本              | 1.1.0                                                       | 1.3.0                                               |                        1.5.0                 |
+| 数据集                     | 1200k张图片                                                 | 1200k张图片                                         |                       1200k图片                        |
+| 训练参数                   | epoch=500, steps=1251, batch_size=128, lr=0.1               | epoch=500, steps=1251, batch_size = 128, lr=0.005   |            epoch=500, steps=10009, batch_size=128, lr=0.1                |
+| 优化器                     | Momentum                                                    | Momentum                                            |                      Momentum                   |
+| 损失函数                   | Softmax Cross Entropy                                       | Softmax Cross Entropy                               |                   Softmax Cross Entropy                  |
+| 速度                       | 8卡: 104 ms/step                                            | 8卡: 255 ms/step                                    |                          单卡:11081 ms/step                     |
+| 总时间                     | 8卡: 17.8小时                                               | 8卡: 46.9小时                                       |                             > 200小时                    |
+| 参数(M)                    | 4.0;                                                        | 4.0;                                              |                             4.0;                       |
 | 脚本                       | [Tiny-Darknet脚本](https://gitee.com/mindspore/models/tree/master/official/cv/tinydarknet)
 
 ### [评估性能](#目录)
 
-| 参数                | Ascend                            | GPU                               |
-| ------------------- | ----------------------------------| ----------------------------------|
-| 模型版本            | V1                                | V1                                |
-| 资源                |  Ascend 910;系统 Euler2.8        | NV SMX2 V100-32G                  |
-| 上传日期            | 2020/12/22                        | 2021/7/15                         |
-| MindSpore版本       | 1.1.0                             | 1.3.0                             |
-| 数据集              | 200k张图片                        | 200k张图片                        |
-| batch_size          | 128                               | 128                               |
-| 输出                | 分类概率                          | 分类概率                          |
-| 准确率              | 8卡 Top-1: 58.7%; Top-5: 81.7%    | 8卡 Top-1: 58.9%; Top-5: 81.7%    |
-| 推理模型            | 11.6M (.ckpt文件)                 | 10.06M (.ckpt文件)                |
+| 参数                | Ascend                            | GPU                               |                  CPU            |
+| ------------------- | ----------------------------------| ----------------------------------|--------------------------------|
+| 模型版本            | V1                                | V1                                |                                  |
+| 资源                |  Ascend 910;系统 Euler2.8        | NV SMX2 V100-32G                  |       CPU 72cores, 内存 503G      |
+| 上传日期            | 2020/12/22                        | 2021/7/15                         |             2020/12/22           |
+| MindSpore版本       | 1.1.0                             | 1.3.0                             |             1.5.0               |
+| 数据集              | 200k张图片                        | 200k张图片                        |              200k张图片             |
+| batch_size          | 128                               | 128                               |            128                  |
+| 输出                | 分类概率                          | 分类概率                          |               分类概率              |
+| 准确率              | 8卡 Top-1: 58.7%; Top-5: 81.7%    | 8卡 Top-1: 58.9%; Top-5: 81.7%    |   单卡 Top-1: 58.7%; Top-5:81.5  |
+| 推理模型            | 11.6M (.ckpt文件)                 | 10.06M (.ckpt文件)                |             11.6M (.ckpt文件)      |
 
 ### [推理性能](#目录)
 
diff --git a/official/cv/tinydarknet/scripts/run_distribute_train.sh b/official/cv/tinydarknet/scripts/run_distribute_train.sh
index 28ffe26789d8457382c93a2b79ffcf2df08b9322..5c9ed77243bbb04713518b3a949edaf12ecc9dd2 100644
--- a/official/cv/tinydarknet/scripts/run_distribute_train.sh
+++ b/official/cv/tinydarknet/scripts/run_distribute_train.sh
@@ -14,31 +14,38 @@
 # limitations under the License.
 # ============================================================================
 
-echo "$1 $2"
+echo "$1 $2 $3"
 
-if [ $# != 1 ] && [ $# != 2 ]
+if [ $# != 3 ]
 then
-    echo "Usage: bash run_distribute_train.sh [RANK_TABLE_FILE] [cifar10|imagenet]"
+    echo "Usage: bash run_distribute_train.sh [RANK_TABLE_FILE] [cifar10|imagenet] [TRAIN_DATA_DIR]"
 exit 1
 fi
 
 if [ ! -f $1 ]
 then
-    echo "error:RANK_TABLE_FILE=$1 is not a file"
-exit 1
+    echo "error: RANK_TABLE_FILE=$1 is not a file"
+    exit 1
 fi
 
-dataset_type='imagenet'
-if [ $# == 2 ]
-then
-    if [ $2 != "cifar10" ] && [ $2 != "imagenet" ]
-    then
-        echo "error: the selected dataset is neither cifar10 nor imagenet"
+PROJECT_DIR=$(cd ./"`dirname $0`" || exit; pwd)
+if [ $2 == 'imagenet' ]; then
+    CONFIG_FILE="$PROJECT_DIR/../config/imagenet_config.yaml"
+    dataset_type='imagenet'
+elif [ $2 == 'cifar10' ]; then
+    CONFIG_FILE="$PROJECT_DIR/../config/cifar10_config.yaml"
+    dataset_type='cifar10'
+else
+    echo "error: the selected dataset is neither cifar10 nor imagenet"
     exit 1
-    fi
-    dataset_type=$2
 fi
 
+if [ ! -d $3 ]
+then
+    echo "error: TRAIN_DATA_DIR=$3 is not a dir"
+    exit 1
+fi
+data_path=$3
 
 ulimit -u unlimited
 export DEVICE_NUM=8
@@ -61,6 +68,7 @@ do
     echo "start training for rank $RANK_ID, device $DEVICE_ID, $dataset_type"
     cd ./train_parallel$i || exit
     env > env.log
-    python train.py --dataset_name=$dataset_type > log 2>&1 &
+    python train.py --dataset_name=$dataset_type --train_data_dir=$data_path \
+        --config_path=$CONFIG_FILE > log 2>&1 &
     cd ..
-done
\ No newline at end of file
+done
diff --git a/official/cv/tinydarknet/scripts/run_distribute_train_gpu.sh b/official/cv/tinydarknet/scripts/run_distribute_train_gpu.sh
index bb31d5bbd8071cb06b1421f94c954107134f6dfe..41887c1221fdf686cf21feb823179362052b63a7 100644
--- a/official/cv/tinydarknet/scripts/run_distribute_train_gpu.sh
+++ b/official/cv/tinydarknet/scripts/run_distribute_train_gpu.sh
@@ -15,7 +15,7 @@
 # ============================================================================
 
 if [ $# != 3 ]; then
-  echo "Usage: sh run_distribute_train_gpu.sh [RANK_SIZE] [TRAIN_DATA_DIR] [cifar10|imagenet]"
+  echo "Usage: bash run_distribute_train_gpu.sh [RANK_SIZE] [TRAIN_DATA_DIR] [cifar10|imagenet]"
   exit 1
 fi
 
@@ -52,9 +52,9 @@ if [ -d "distribute_train_gpu" ]; then
 fi
 
 mkdir ./distribute_train_gpu
-cp ./*.py ./distribute_train_gpu
-cp -r ./config ./distribute_train_gpu
-cp -r ./src ./distribute_train_gpu
+cp ../*.py ./distribute_train_gpu
+cp -r ../config ./distribute_train_gpu
+cp -r ../src ./distribute_train_gpu
 cd ./distribute_train_gpu || exit
 
 if [ $3 == 'imagenet' ]; then
@@ -68,8 +68,8 @@ fi
 
 mpirun --allow-run-as-root -n $RANK_SIZE --output-filename log_output --merge-stderr-to-stdout \
 nohup python train.py  \
-  --config_path=$CONFIG_FILE \
-  --dataset_name=$dataset_type \
-  --train_data_dir=$TRAIN_DATA_DIR \
-  --device_target=GPU > log.txt 2>&1 &
+    --config_path=$CONFIG_FILE \
+    --dataset_name=$dataset_type \
+    --train_data_dir=$TRAIN_DATA_DIR \
+    --device_target=GPU > log.txt 2>&1 &
 cd ..
\ No newline at end of file
diff --git a/official/cv/tinydarknet/scripts/run_eval.sh b/official/cv/tinydarknet/scripts/run_eval.sh
index 1c5b4fde06ce33ff1b21301c56c748c72d9e337f..365a7446b959341b8d9bb4f73ea56d73b5758491 100644
--- a/official/cv/tinydarknet/scripts/run_eval.sh
+++ b/official/cv/tinydarknet/scripts/run_eval.sh
@@ -14,9 +14,43 @@
 # limitations under the License.
 # ============================================================================
 
-abs_path=$(readlink -f "$0")
-cur_path=$(dirname $abs_path)
-cd $cur_path
+if [ $# != 3 ]
+then
+  echo "Usage: bash run_eval.sh [VAL_DATA_DIR] [cifar10|imagenet] [checkpoint_path]"
+exit 1
+fi
+
+get_real_path(){
+  if [ "${1:0:1}" == "/" ]; then
+    echo "$1"
+  else
+    echo "$(realpath -m $PWD/$1)"
+  fi
+}
+
+PATH1=$(get_real_path $1)
+if [ ! -d $PATH1 ]
+then
+  echo "error: VAL_DATA_DIR=$PATH1 is not a directory"
+exit 1
+fi
+
+PATH2=$(get_real_path $3)
+if [ ! -f $PATH2 ]
+then
+    echo "error: CHECKPOINT_PATH=$PATH2 is not a file"
+exit 1
+fi
+
+BASE_PATH=$(dirname "$(dirname "$(readlink -f $0)")")
+if [ $2 == 'imagenet' ]; then
+  CONFIG_FILE="${BASE_PATH}/config/imagenet_config.yaml"
+elif [ $2 == 'cifar10' ]; then
+  CONFIG_FILE="${BASE_PATH}/config/cifar10_config.yaml"
+else
+  echo "error: the selected dataset is neither cifar10 nor imagenet"
+exit 1
+fi
 
 rm -rf ./eval
 mkdir ./eval
@@ -24,6 +58,7 @@ cp -r ../src ./eval
 cp ../eval.py ./eval
 cp -r ../config ./eval
 cd ./eval || exit
-env >env.log
-python ./eval.py > ./eval.log 2>&1 &
+env > env.log
+python ./eval.py  --val_data_dir=$PATH1 --dataset_name=$2 --config_path=$CONFIG_FILE \
+    --checkpoint_path=$PATH2 > ./eval.log 2>&1 &
 cd ..
diff --git a/official/cv/tinydarknet/scripts/run_eval_cpu.sh b/official/cv/tinydarknet/scripts/run_eval_cpu.sh
index a4aef5fffb6b79ae8965c71c2dc1f17e7dafaebb..b6982f9417ff34edd3cfdeca64ef89d219d25a48 100644
--- a/official/cv/tinydarknet/scripts/run_eval_cpu.sh
+++ b/official/cv/tinydarknet/scripts/run_eval_cpu.sh
@@ -15,7 +15,7 @@
 # ============================================================================
 if [ $# != 1 ] && [ $# != 2 ]  && [ $# != 3 ]
 then
-  echo "Usage bash scripts/run_eval_cpu.sh [VAL_DATA_DIR] [cifar10|imagenet] [checkpoint_path]"
+  echo "Usage: bash run_eval_cpu.sh [VAL_DATA_DIR] [cifar10|imagenet] [checkpoint_path]"
 exit 1
 fi
 
@@ -53,12 +53,12 @@ fi
 
 rm -rf ./eval
 mkdir ./eval
-cp -r ./src ./eval
-cp ./eval.py ./eval
-cp -r ./config ./eval
-env >env.log
+cp -r ../src ./eval
+cp ../eval.py ./eval
+cp -r ../config ./eval
+env > env.log
 echo "start evaluation for device CPU"
 cd ./eval || exit
 python ./eval.py --device_target=CPU --val_data_dir=$PATH1 --dataset_name=$2 --config_path=$CONFIG_FILE \
---checkpoint_path=$PATH2 > ./eval.log 2>&1 &
+    --checkpoint_path=$PATH2 > ./eval.log 2>&1 &
 cd ..
diff --git a/official/cv/tinydarknet/scripts/run_eval_gpu.sh b/official/cv/tinydarknet/scripts/run_eval_gpu.sh
index 1075aa1e31e7d04648c7a7eca782067ce43155f9..27eefd850aca419658258cfc318b436b731f29d4 100644
--- a/official/cv/tinydarknet/scripts/run_eval_gpu.sh
+++ b/official/cv/tinydarknet/scripts/run_eval_gpu.sh
@@ -13,9 +13,9 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 # ============================================================================
-if [ $# != 1 ] && [ $# != 2 ]  && [ $# != 3 ]
+if [ $# != 3 ]
 then
-  echo "Usage bash scripts/run_train_gpu.sh [VAL_DATA_DIR] [cifar10|imagenet] [checkpoint_path]"
+  echo "Usage: bash run_eval_gpu.sh [VAL_DATA_DIR] [cifar10|imagenet] [checkpoint_path]"
 exit 1
 fi
 
@@ -53,12 +53,12 @@ fi
 
 rm -rf ./eval
 mkdir ./eval
-cp -r ./src ./eval
-cp ./eval.py ./eval
-cp -r ./config ./eval
-env >env.log
+cp -r ../src ./eval
+cp ../eval.py ./eval
+cp -r ../config ./eval
+env > env.log
 echo "start evaluation for device GPU"
 cd ./eval || exit
 python ./eval.py --device_target=GPU --val_data_dir=$PATH1 --dataset_name=$2 --config_path=$CONFIG_FILE \
---checkpoint_path=$PATH2 > ./eval.log 2>&1 &
+    --checkpoint_path=$PATH2 > ./eval.log 2>&1 &
 cd ..
diff --git a/official/cv/tinydarknet/scripts/run_standalone_train.sh b/official/cv/tinydarknet/scripts/run_standalone_train.sh
index 91b2e04c47ba81f9486820afb80628f28c55743b..b8db4a8a57beb5ce8c22f8c9fbb00cfb9e38926d 100644
--- a/official/cv/tinydarknet/scripts/run_standalone_train.sh
+++ b/official/cv/tinydarknet/scripts/run_standalone_train.sh
@@ -18,7 +18,7 @@ echo "$1 $2 $3"
 
 if [ $# != 2 ] && [ $# != 3 ]
 then
-    echo "Usage: bash run_distribute_train.sh [DEVICE_ID] [TRAIN_DATA_DIR] [cifar10|imagenet]"
+    echo "Usage: bash run_standalone_train.sh [DEVICE_ID] [TRAIN_DATA_DIR] [cifar10|imagenet]"
 exit 1
 fi
 
@@ -36,15 +36,16 @@ exit 1
 fi
 train_data_dir=$2
 
-dataset_type='imagenet'
-if [ $# == 3 ]
-then
-    if [ $3 != "cifar10" ] && [ $3 != "imagenet" ]
-    then
-        echo "error: the selected dataset is neither cifar10 nor imagenet"
+PROJECT_DIR=$(cd ./"`dirname $0`" || exit; pwd)
+if [ $3 == 'imagenet' ]; then
+    CONFIG_FILE="$PROJECT_DIR/../config/imagenet_config.yaml"
+    dataset_type='imagenet'
+elif [ $3 == 'cifar10' ]; then
+    CONFIG_FILE="$PROJECT_DIR/../config/cifar10_config.yaml"
+    dataset_type='cifar10'
+else
+    echo "error: the selected dataset is neither cifar10 nor imagenet"
     exit 1
-    fi
-    dataset_type=$3
 fi
 
 export DEVICE_ID=$1
@@ -58,4 +59,5 @@ cp ../train.py ./train_single
 cp -r ../config ./train_single
 echo "start training for rank $RANK_ID, device $DEVICE_ID, $dataset_type"
 cd ./train_single || exit
-python ./train.py --dataset_name=$dataset_type --train_data_dir=$train_data_dir> ./train.log 2>&1 &
+python ./train.py --dataset_name=$dataset_type --train_data_dir=$train_data_dir \
+    --config_path=$CONFIG_FILE > ./train.log 2>&1 &
diff --git a/official/cv/tinydarknet/scripts/run_standalone_train_gpu.sh b/official/cv/tinydarknet/scripts/run_standalone_train_gpu.sh
index 513ce25ab6a87cd17611c345614b335d178d2e2d..40bbfbbaa0ace41a2346553968fc8311e16e81d2 100644
--- a/official/cv/tinydarknet/scripts/run_standalone_train_gpu.sh
+++ b/official/cv/tinydarknet/scripts/run_standalone_train_gpu.sh
@@ -18,7 +18,7 @@ echo "$1 $2 $3"
 
 if [ $# != 2 ] && [ $# != 3 ]
 then
-    echo "Usage: bash run_distribute_train_gpu.sh [DEVICE_ID] [TRAIN_DATA_DIR] [cifar10|imagenet]"
+    echo "Usage: bash run_standalone_train_gpu.sh [DEVICE_ID] [TRAIN_DATA_DIR] [cifar10|imagenet]"
 exit 1
 fi
 
@@ -49,12 +49,12 @@ then
 fi
 
 if [ $3 == 'imagenet' ]; then
-  CONFIG_FILE="$PROJECT_DIR/../config/imagenet_config_gpu.yaml"
+    CONFIG_FILE="$PROJECT_DIR/../config/imagenet_config_gpu.yaml"
 elif [ $3 == 'cifar10' ]; then
-  CONFIG_FILE="$PROJECT_DIR/../config/cifar10_config_gpu.yaml"
+    CONFIG_FILE="$PROJECT_DIR/../config/cifar10_config_gpu.yaml"
 else
-  echo "error: the selected dataset is neither cifar10 nor imagenet"
-exit 1
+    echo "error: the selected dataset is neither cifar10 nor imagenet"
+    exit 1
 fi
 
 export DEVICE_ID=$1
@@ -69,5 +69,5 @@ cp -r ../config ./train_single_gpu
 echo "start training for rank $RANK_ID, device $DEVICE_ID, $dataset_type"
 cd ./train_single_gpu || exit
 python ./train.py --config_path=$CONFIG_FILE \
---dataset_name=$dataset_type --train_data_dir=$train_data_dir --device_target=GPU> ./train.log 2>&1 &
+    --dataset_name=$dataset_type --train_data_dir=$train_data_dir --device_target=GPU> ./train.log 2>&1 &
 
diff --git a/official/cv/tinydarknet/scripts/run_train_cpu.sh b/official/cv/tinydarknet/scripts/run_train_cpu.sh
index cb01a8b7a9c62118bc2c9a476606f091146cda5b..5fa428a4f32332c759abeab521f4ca00b2db26dc 100644
--- a/official/cv/tinydarknet/scripts/run_train_cpu.sh
+++ b/official/cv/tinydarknet/scripts/run_train_cpu.sh
@@ -16,7 +16,7 @@
 
 if [ $# != 1 ] && [ $# != 2 ]
 then
-  echo "Usage bash scripts/run_train_cpu.sh [TRAIN_DATA_DIR] [cifar10|imagenet]"
+  echo "Usage bash run_train_cpu.sh [TRAIN_DATA_DIR] [cifar10|imagenet]"
 exit 1
 fi
 
@@ -47,11 +47,12 @@ fi
 
 rm -rf ./train_cpu
 mkdir ./train_cpu
-cp ./train.py ./train_cpu
-cp -r ./src ./train_cpu
-cp -r ./config ./train_cpu
+cp ../train.py ./train_cpu
+cp -r ../src ./train_cpu
+cp -r ../config ./train_cpu
 echo "start training for device CPU"
 cd ./train_cpu || exit
 env > env.log
-python train.py --device_target=CPU --train_data_dir=$PATH1 --dataset_name=$2 --config_path=$CONFIG_FILE> ./train.log 2>&1 &
+python train.py --device_target=CPU --train_data_dir=$PATH1 --dataset_name=$2 \
+    --config_path=$CONFIG_FILE> ./train.log 2>&1 &
 cd ..