add introduction for the use of preprocess_dataset.py

model_zoo/official/cv/unet/README.md

@@ -98,12 +98,12 @@ If set `split`=1.0, you should split train dataset and val dataset by directorie
 
 We support script to convert COCO and a Cell_Nuclei dataset used in used in [Unet++ original paper](https://arxiv.org/abs/1912.05074) to mulyi-class dataset format.
 
-1. Select `*yaml` in `unet`.
+1. Select `*.yaml` file under `unet` and modify the parameters as needed.
 
 2. run script to convert to mulyi-class dataset format:
 
 ```shell
-python preprocess_dataset.py -d /data/save_data_path
+python preprocess_dataset.py --config_path path/unet/*.yaml  --data_path /data/save_data_path
 ```
 
 ## [Environment Requirements](#contents)
@@ -481,7 +481,7 @@ Export MindIR on local
 Before exporting, you need to modify the parameter in the configuration — checkpoint_file_path and batch_ Size . checkpoint_ file_ Path is the CKPT file path, batch_ Size is set to 1.
 
 ```shell
-python export.py --config_path=[CONFIG_PATH]
+python export.py --config_path=[CONFIG_PATH] --checkpoint_file_path=[model_ckpt_path] --file_name=[air_model_name] --file_format=AIR
 ```
 
 The checkpoint_file_path parameter is required,

model_zoo/official/cv/unet/README_CN.md

@@ -102,12 +102,12 @@ UNet++是U-Net的增强版本，使用了新的跨层链接方式和深层监督
 
 我们提供了一个脚本来将 COCO 和 Cell_Nuclei 数据集（[Unet++ 原论文](https://arxiv.org/abs/1912.05074) 中使用）转换为multi-class格式。
 
-1. 在`src/model_utils/`下选择对应的yaml文件。
+1. 在unet下选择*.yaml文件，根据需要修改参数。
 
 2. 运行转换脚本:
 
 ```shell
-python preprocess_dataset.py -d /data/save_data_path
+python preprocess_dataset.py --config_path path/unet/*.yaml  --data_path /data/save_data_path
 ```
 
 ## 环境要求
@@ -480,7 +480,7 @@ python eval.py --data_path=/path/to/data/ --checkpoint_file_path=/path/to/checkp
 本地导出mindir
 
 ```shell
-python export.py --config_path=[CONFIG_PATH]
+python export.py --config_path=[CONFIG_PATH] --checkpoint_file_path=[model_ckpt_path] --file_name=[air_model_name] --file_format=AIR
 ```
 
 ModelArts导出mindir

model_zoo/official/cv/unet/preprocess_dataset.py

@@ -19,7 +19,7 @@ Images within one folder is an image, the image file named `"image.png"`, the ma
 import os
 import cv2
 import numpy as np
-from model_zoo.official.cv.unet.src.model_utils.config import config
+from src.model_utils.config import config
 
 def annToMask(ann, height, width):
     """Convert annotation to RLE and then to binary mask."""