Refine docs

Dockerfile

@@ -1,5 +1,5 @@
 # 0. set args
-ARG PPTAG=2.4.1  # tags refers to https://hub.docker.com/r/paddlepaddle/paddle/tags
+ARG PPTAG=2.4.1  # tags refer to https://hub.docker.com/r/paddlepaddle/paddle/tags
 
 # 1. pull base image
 FROM paddlepaddle/paddle:${PPTAG}

README_CN.md

@@ -139,7 +139,7 @@ PaddleRS具有以下五大特色：
           <li>ResizeByLong</li>
           <li>ResizeByShort</li>
           <li>SelectBand（波段选择）</li>
-          <li><a href="./docs/intro/transforms.md">...</a></li>
+          <li><a href="./docs/intro/transforms_cn.md">...</a></li>
         </ul>
         </details>
         <details><summary><b>数据增强</b></summary>
@@ -156,7 +156,7 @@ PaddleRS具有以下五大特色：
           <li>RandomScaleAspect</li>
           <li>RandomSwap（随机时序交换）</li>
           <li>RandomVerticalFlip</li>
-          <li><a href="./docs/intro/transforms.md">...</a></li>
+          <li><a href="./docs/intro/transforms_cn.md">...</a></li>
         </ul>
         </details>
         <details><summary><b>遥感指数</b></summary>
@@ -208,7 +208,7 @@ PaddleRS具有以下五大特色：
           <li>WI1</li>
           <li>WI2</li>
           <li>WRI</li>
-          <li><a href="./docs/intro/indices.md">...</a></li>
+          <li><a href="./docs/intro/indices_cn.md">...</a></li>
         </ul>
         </details>
       </td>
@@ -248,7 +248,7 @@ PaddleRS具有以下五大特色：
           <li><a href="./tools/prepare_dataset/prepare_ucmerced.py">UC Merced</a></li>
           <li><a href="./tools/prepare_dataset/prepare_rsod.py">RSOD</a></li>
           <li><a href="./tools/prepare_dataset/prepare_isaid.py">iSAID</a></li>
-          <li><a href="./docs/intro/data_prep.md">...</a></li>
+          <li><a href="./docs/intro/data_prep_cn.md">...</a></li>
         </ul>
       </td>
       <td>
@@ -272,27 +272,27 @@ PaddleRS具有以下五大特色：
 ## <img src="./docs/images/teach.png" width="30"/> 教程与文档
 
 * 快速上手
-  * [快速上手PaddleRS](./docs/quick_start.md)
+  * [快速上手PaddleRS](./docs/quick_start_cn.md)
 * 数据准备
-  * [快速了解遥感与遥感数据](./docs/data/rs_data.md)
-  * [开源遥感数据集汇总表](./docs/data/dataset.md)
+  * [快速了解遥感与遥感数据](./docs/data/rs_data_cn.md)
+  * [开源遥感数据集汇总表](./docs/data/dataset_cn.md)
   * [智能标注工具EISeg](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.7/EISeg)
-  * [遥感影像处理工具集](./docs/data/tools.md)
+  * [遥感影像处理工具集](./docs/data/tools_cn.md)
 * 组件介绍
-  * [数据集预处理脚本](./docs/intro/data_prep.md)
-  * [模型库](./docs/intro/model_zoo.md)
-  * [遥感指数](./docs/intro/indices.md)
-  * [数据变换算子](./docs/intro/transforms.md)
-* [模型训练](./tutorials/train/README.md)
+  * [数据集预处理脚本](./docs/intro/data_prep_cn.md)
+  * [模型库](./docs/intro/model_zoo_cn.md)
+  * [遥感指数](./docs/intro/indices_cn.md)
+  * [数据变换算子](./docs/intro/transforms_cn.md)
+* [模型训练](./tutorials/train/README_CN.md)
 * 模型部署
   * [模型导出](./deploy/export/README.md)
   * [Python部署](./deploy/README.md)
 * 代码贡献
-  * [贡献指南](./docs/CONTRIBUTING.md)
-  * [开发指南](./docs/dev/dev_guide.md)
-  * [代码注释规范](./docs/dev/docstring.md)
-  * [模型训练API说明](./docs/apis/train.md)
-  * [模型推理API说明](./docs/apis/infer.md)
+  * [贡献指南](./docs/CONTRIBUTING_CN.md)
+  * [开发指南](./docs/dev/dev_guide_cn.md)
+  * [代码注释规范](./docs/dev/docstring_cn.md)
+  * [模型训练API说明](./docs/apis/train_cn.md)
+  * [模型推理API说明](./docs/apis/infer_cn.md)
 
 ## <img src="./docs/images/anli.png" width="30"/> 实践案例
 

README_EN.md

@@ -60,7 +60,7 @@ PaddleRS is an end-to-end high-efficent development toolkit for remote sensing a
         <b>Models</b>
       </td>
       <td>
-        <b>Data Transforming Operators</b>
+        <b>Data Transformation Operators</b>
       </td>
       <td>
         <b>Remote Sensing Data Tools</b>
@@ -137,7 +137,7 @@ PaddleRS is an end-to-end high-efficent development toolkit for remote sensing a
           <li>ResizeByLong</li>
           <li>ResizeByShort</li>
           <li>SelectBand</li>
-          <li><a href="./docs/intro/transforms.md">...</a></li>
+          <li><a href="./docs/intro/transforms_en.md">...</a></li>
         </ul>
         </details>
         <details><summary><b>Data Augmentation</b></summary>
@@ -154,7 +154,7 @@ PaddleRS is an end-to-end high-efficent development toolkit for remote sensing a
           <li>RandomScaleAspect</li>
           <li>RandomSwap</li>
           <li>RandomVerticalFlip</li>
-          <li><a href="./docs/intro/transforms.md">...</a></li>
+          <li><a href="./docs/intro/transforms_en.md">...</a></li>
         </ul>
         </details>
         <details><summary><b>Remote Sensing Indices</b></summary>
@@ -206,7 +206,7 @@ PaddleRS is an end-to-end high-efficent development toolkit for remote sensing a
           <li>WI1</li>
           <li>WI2</li>
           <li>WRI</li>
-          <li><a href="./docs/intro/indices.md">...</a></li>
+          <li><a href="./docs/intro/indices_en.md">...</a></li>
         </ul>
         </details>
       </td>
@@ -246,7 +246,7 @@ PaddleRS is an end-to-end high-efficent development toolkit for remote sensing a
           <li><a href="./tools/prepare_dataset/prepare_ucmerced.py">UC Merced</a></li>
           <li><a href="./tools/prepare_dataset/prepare_rsod.py">RSOD</a></li>
           <li><a href="./tools/prepare_dataset/prepare_isaid.py">iSAID</a></li>
-          <li><a href="./docs/intro/data_prep.md">...</a></li>
+          <li><a href="./docs/intro/data_prep_en.md">...</a></li>
         </ul>
       </td>
       <td>
@@ -270,26 +270,26 @@ PaddleRS is an end-to-end high-efficent development toolkit for remote sensing a
 ## <img src="./docs/images/teach.png" width="30"/> Tutorials and Documents
 
 * Quick Start
-  * [Quick start](./docs/quick_start.md)
+  * [Quick start](./docs/quick_start_en.md)
 * Data Preparation
-  * [Open-source remote sensing datasets](./docs/data/dataset.md)
+  * [Open-source remote sensing datasets](./docs/data/dataset_en.md)
   * [Efficient interactive segmentation tool EISeg](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.7/EISeg)
-  * [Remote sensing data tools](./docs/data/tools.md)
+  * [Remote sensing data tools](./docs/data/tools_en.md)
 * Introduction on Components
-  * [Data preprocessing tools](./docs/intro/data_prep.md)
-  * [Models](./docs/intro/model_zoo.md)
-  * [Remote sensing indices](./docs/intro/indices.md)
-  * [Data transforming operators](./docs/intro/transforms.md)
-* [Model Training](./tutorials/train/README.md)
+  * [Data preprocessing tools](./docs/intro/data_prep_en.md)
+  * [Models](./docs/intro/model_zoo_en.md)
+  * [Remote sensing indices](./docs/intro/indices_en.md)
+  * [Data transforming operators](./docs/intro/transforms_en.md)
+* [Model Training](./tutorials/train/README_EN.md)
 * Model Deployment
   * [Model export](./deploy/export/README.md)
   * [Paddle Inference (Python)](./deploy/README.md)
 * Development and Contribution
-  * [Contributing guides](./docs/CONTRIBUTING.md)
-  * [Development manual](./docs/dev/dev_guide.md)
-  * [Code style guides](./docs/dev/docstring.md)
-  * [Training APIs](./docs/apis/train.md)
-  * [Inference APIs](./docs/apis/infer.md)
+  * [Contributing guides](./docs/CONTRIBUTING_EN.md)
+  * [Development manual](./docs/dev/dev_guide_en.md)
+  * [Code style guides](./docs/dev/docstring_en.md)
+  * [Training APIs](./docs/apis/train_en.md)
+  * [Inference APIs](./docs/apis/infer_en.md)
 
 ## <img src="./docs/images/anli.png" width="30"/> Application Examples
 

deploy/README.md

@@ -55,7 +55,7 @@ res = predictor.predict(("demo_data/A.png", "demo_data/B.png"))
 cm_1024x1024 = res['label_map']
 ```
 
-请注意，**`predictor.predict()`方法接受的影像列表长度与导出模型时指定的batch size必须一致**（若指定的batch size不为-1），这是因为`Predictor`对象将所有输入影像拼接成一个batch执行预测。您可以在[模型推理API说明](https://github.com/PaddlePaddle/PaddleRS/blob/develop/docs/apis/infer.md)中了解关于`predictor.predict()`方法返回结果格式的更多信息。
+请注意，**`predictor.predict()`方法接受的影像列表长度与导出模型时指定的batch size必须一致**（若指定的batch size不为-1），这是因为`Predictor`对象将所有输入影像拼接成一个batch执行预测。您可以在[模型推理API说明](https://github.com/PaddlePaddle/PaddleRS/blob/develop/docs/apis/infer_cn.md)中了解关于`predictor.predict()`方法返回结果格式的更多信息。
 
 ### 2.2 指定预热轮数与重复次数
 

docs/CONTRIBUTING.md → docs/CONTRIBUTING_CN.md

@@ -1,3 +1,5 @@
+简体中文 | [English](CONTRIBUTING_EN.md)
+
 # PaddleRS贡献指南
 
 ## 贡献代码
@@ -6,12 +8,12 @@
 
 ### 1 代码贡献步骤
 
-PaddleRS使用[git](https://git-scm.com/doc)作为版本控制工具，并托管在GitHub平台。这意味着，在贡献代码前，您需要熟悉git相关操作，并且对以[pull request (PR)](https://docs.github.com/cn/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/about-pull-requests)为基础的GitHub工作流有所了解。
+PaddleRS使用[Git](https://git-scm.com/doc)作为版本控制工具，并托管在GitHub平台。这意味着，在贡献代码前，您需要熟悉git相关操作，并且对以[pull request (PR)](https://docs.github.com/cn/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/about-pull-requests)为基础的GitHub工作流有所了解。
 
 为PaddleRS贡献代码的具体步骤如下：
 
 1. 在GitHub上fork PaddleRS官方仓库，将代码克隆到本地，并拉取develop分支的最新版本。
-2. 根据[《开发指南》](dev/dev_guide.md)编写代码（建议在新建的功能分支上开发）。
+2. 根据[《开发指南》](dev/dev_guide_cn.md)编写代码（建议在新建的功能分支上开发）。
 3. 安装pre-commit钩子以便在每次commit前执行代码风格方面的检查。详见[代码风格规范](#3-代码风格规范)。
 4. 为新增的代码编写单元测试，并保证所有测试能够跑通。详见[测试相关步骤](#4-测试相关步骤)。
 5. 为您的分支新建一个PR，确保CLA协议签署且CI/CE通过。在这之后，会有PaddleRS团队人员对您贡献的代码进行review。
@@ -70,7 +72,7 @@ from paddlers.transforms import DecodeImg
 
 PaddleRS对代码风格的规范基本与[Google Python风格规范](https://zh-google-styleguide.readthedocs.io/en/latest/google-python-styleguide/python_style_rules/)一致，但PaddleRS对类型注解（即type hints，参见[PEP 483](https://peps.python.org/pep-0483/)与[PEP 484](https://peps.python.org/pep-0484/)）不做强制要求。较为重要的代码风格规范如下：
 
-- 空行：顶层定义（例如顶层的函数或者类的定义）之间空2行。类内部不同方法的定义之间、以及类名与第一个方法定义之间空1行。在函数内部需要注意在逻辑上有间断的地方添加1个空行。
+- 空行：顶层定义（例如顶层的函数或者类的定义）之间空2行。类内部不同方法的定义之间空1行。在函数内部需要注意在逻辑上有间断的地方添加1个空行。
 
 - 行长度：每行（无论是代码行还是注释行）不超过80个字符，对于docstring中的行尤其要注意这一点。
 
@@ -78,7 +80,7 @@ PaddleRS对代码风格的规范基本与[Google Python风格规范](https://zh-
 
 - 异常：抛出和捕获异常时使用尽可能具体的异常类型，几乎永远不要使用基类`Exception`（除非目的是捕获不限类型的任何异常）。
 
-- 注释：所有注释使用英文书写。所有提供给用户的API都必须添加docstring，且至少具有“API功能描述”和“API参数”两个部分。使用三双引号`"""`包围一个docstring。docstring书写的具体细节可参考[《代码注释规范》](dev/docstring.md)。
+- 注释：所有注释使用英文书写。所有提供给用户的API都必须添加docstring，且至少具有“API功能描述”和“API参数”两个部分。使用三双引号`"""`包围一个docstring。docstring书写的具体细节可参考[《代码注释规范》](dev/docstring_cn.md)。
 
 - 命名：不同类型的变量名适用的大小写规则如下：模块名：`module_name`；包名：`package_name`；类名：`ClassName`；方法名：`method_name`；函数名：`function_name`；全局常量（指程序运行期间值不发生改变的变量）名：`GLOBAL_CONSTANT_NAME`；全局变量名：`global_var_name`；实例名：`instance_var_name`；函数参数名：`function_param_name`；局部变量名：`local_var_name`。
 

docs/CONTRIBUTING_en.md → docs/CONTRIBUTING_EN.md

@@ -1,3 +1,5 @@
+[简体中文](CONTRIBUTING_CN.md) | English
+
 # PaddleRS Contribution Guide
 
 ## Contribute Code
@@ -6,18 +8,18 @@ This guide starts with the necessary steps to contribute code to PaddleRS, and t
 
 ### 1 Code Contribution Steps
 
-PaddleRS uses [git](https://git-scm.com/doc) as a version control tool and is hosted on GitHub. This means that you need to be familiar with git before contributing code. And you need to be familiar with [pull request (PR)](https://docs.github.com/cn/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/about-pull-requests) based on the GitHub workflow.
+PaddleRS uses [Git](https://git-scm.com/doc) as a version control tool and is hosted on GitHub. This means that you need to be familiar with git before contributing code. And you need to be familiar with [pull request (PR)](https://docs.github.com/cn/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/about-pull-requests) based on the GitHub workflow.
 
 The steps to contribute code to PaddleRS are as follows:
 
-1. Fork the official PaddleRS repository on GitHub, clone the code locally, and pull the latest version of the develop branch.
-2. Write code according to [Dev Guide](dev/dev_guide.md) (it is recommended to develop on a new feature branch).
-3. Install pre-commit hooks to perform code style checks before each commit. Refer to [Code style specification](#3-Code style specification).
-4. Write unit tests for the new code and make sure all the tests are successful. Refer to [Test related steps](#4-Test related steps)。
-5. Create a new PR for your branch and ensure that the CLA protocol is signed and the CI/CE passes. After that, a PaddleRS team member will review the code you contributed.
+1. Fork the official PaddleRS repository on GitHub, clone the code locally, and pull the develop branch.
+2. Write code according to [Dev Guide](dev/dev_guide_en.md) (it is recommended to develop on a new feature branch).
+3. Install pre-commit hooks to perform code style checks before each commit. Refer to [Code style specification](#3-code-style-specification).
+4. Write unit tests for the new code and make sure all the tests are successful. Refer to [Test related steps](#4-test-related-steps)。
+5. Create a new PR for your branch and ensure that the CLA is signed and the CI/CE finish with no errors. After that, a PaddleRS team member will review the code you contributed.
 6. Modify the code according to the review and resubmit it until PR is merged or closed.
 
-If you contribute code that uses a third-party library that PaddleRS does not currently rely on, please explain when you submit your PR. Also, you should explain why this third-party library should be used.
+If you contribute code that uses a third-party library that PaddleRS does not currently rely on, please explain when you submit your PR. Also, you should explain why this third-party library need to be used.
 
 ### 2 Self-Check on Added Files
 
@@ -68,9 +70,9 @@ from paddlers.transforms import DecodeImg
 
 ### 3 Code Style Specification
 
-PaddleRS' code style specification is basically the same as the [Google Python Style specification](https://zh-google-styleguide.readthedocs.io/en/latest/google-python-styleguide/python_style_rules/), except that PaddleRS does not enforce the type annotation.(i.e. type hints, refer to [PEP 483](https://peps.python.org/pep-0483/) and [PEP 484](https://peps.python.org/pep-0484/)). Some of the important code style specifications are:
+PaddleRS' code style specification is basically the same as the [Google Python Style specification](https://zh-google-styleguide.readthedocs.io/en/latest/google-python-styleguide/python_style_rules/), except that PaddleRS does not enforce type annotation (i.e. type hints, refer to [PEP 483](https://peps.python.org/pep-0483/) and [PEP 484](https://peps.python.org/pep-0484/)). Some of the important code style specifications are:
 
-- Blank line: Two empty lines between top-level definitions (such as top-level function or class definitions). There is a blank line between the definitions of different methods within the class, and between the class name and the first method definition. Inside the function you need to be careful to add a blank line where there is a logical break.
+- Blank line: Two empty lines between top-level definitions (such as top-level function or class definitions). There should be a blank line between the definitions of different methods within the class. Inside the function you need to be careful to add a blank line where there is a logical break.
 
 - Line length: No more than 80 characters per line (either code or comment), especially for lines in a docstring.
 
@@ -78,27 +80,27 @@ PaddleRS' code style specification is basically the same as the [Google Python S
 
 - Exceptions: Throw and catch exceptions with as specific an exception type as possible, and almost never use the base class `Exception` (unless the purpose is to catch any exception of any type).
 
-- Comments: All comments are written in English. All apis provided to users must have docstrings added and have at least two sections, "API Function Description" and "API Parameters". Surround a docstring with three double quotes `"""`. See the [Code Comment Specification](dev/docstring.md) for details on docstring writing.
+- Comments: All comments should be written in English. All apis provided to users must have docstrings added with at least two sections, "API Function Description" and "API Parameters". Surround a docstring with three double quotes `"""`. See the [Code Comment Specification](dev/docstring_en.md) for details on docstring writing.
 
 - Naming: Variable names of different types apply the following case rules: module name: `module_name`; package name: `package_name`; class name: `ClassName`; method name: `method_name`; function name: `function_name`; name of a global constant (a variable whose value does not change during the running of the program) : `GLOBAL_CONSTANT_NAME`; global variable name: `global_var_name`; instance name: `instance_var_name`; function parameter name: `function_param_name`; local variable name: `local_var_name`.
 
 ### 4 Test Related Steps
 
-To ensure code quality, you need to write unit test scripts for the new functional components. Please read the steps for writing a single test according to your contribution.
+To ensure code quality, the contributor is required to add unit test cases for the new functional components. Please read the steps according to your contribution.
 
-#### 4.1 model Single Test
+#### 4.1 Unit Tests for Models
 
-1. Find the test case definition file corresponding to the task of the model in `tests/rs_models/`, for example, the change detection task corresponding to `tests/rs_models/test_cd_models.py`.
+1. Find the test case definition file corresponding to the task of the model in `tests/rs_models/`. For example, the change detection task corresponds to `tests/rs_models/test_cd_models.py`.
 2. Define a test class for the new model that inherits from `Test{task name}Model` and sets its `MODEL_CLASS` property to the new model, following the example already in the file.
-3. Override the new test class's `test_specs()` method. This method sets `self.specs` to a list with each item in the list as a dictionary whose key-value pairs are used as configuration items for the constructor model. That is, each item in `self.specs` corresponds to a set of test cases, each of which tests the model constructed with a particular parameter.
+3. Override the new test class's `test_specs()` method. This method sets `self.specs` to a list with each item in the list as a dictionary, whose key-value pairs are used as configuration items for the constructor model. That is, each item in `self.specs` corresponds to a set of test cases, each of which tests the model constructed with a particular set of parameters.
 
-#### 4.2 Data Preprocessing/Data Augmentation Single Test
+#### 4.2 Unit Tests for Data Preprocessing/Data Augmentation Functions and Operators
 
-- If you write the data preprocessing/augmentation operator (inherited from `paddlers.transforms.operators.Transform`), all the necessary to construct the operator input parameters have default values, and the operator can handle any task, arbitrary band data, You need to add a new method to the `TestTransform` class in the `tests/transforms/test_operators.py` modulated on the `test_Resize()` or `test_RandomFlipOrRotate()` methods.
-- If you write an operator that only supports processing for a specific task or requires the number of bands in the input data, bind the operator `_InputFilter` in the `OP2FILTER` global variable after writing the test logic.
-- If you are writing a data preprocessing/data augmentation function(i.e. `paddlers/transforms/functions.py`), add a test class in `tests/transforms/test_functions.py` mimicking the existing example.
+- If you contribute an data preprocessing/augmentation operator (inherited from `paddlers.transforms.operators.Transform`), all the necessary input parameters to construct the operator have default values, and the operator can handle any task and arbitrary number of bands, then you need to add a new method to the `TestTransform` class in the `tests/transforms/test_operators.py`, mimicking the `test_Resize()` or `test_RandomFlipOrRotate()` methods.
+- If you contribute an operator that only supports processing for a specific task or has requirements for the number of bands in the input data, bind the operator with `_InputFilter` in `OP2FILTER`.
+- If you contribute a data preprocessing/data augmentation function (i.e. `paddlers/transforms/functions.py`), add a test class in `tests/transforms/test_functions.py` mimicking the existing example.
 
-#### 4.3 Tool Single Test
+#### 4.3 Unit Tests for Tools
 
 1. Create a new file in the `tests/tools/` directory and name it `test_{tool name}.py`.
 2. Write the test case in the newly created script.

docs/README.md

@@ -1 +0,0 @@
-# PaddleRS文档

docs/README.md

@@ -0,0 +1 @@
+README_CN.md

docs/README_CN.md

@@ -0,0 +1,3 @@
+简体中文 | [English](README_EN.md)
+
+# PaddleRS文档

docs/README_EN.md

@@ -0,0 +1,3 @@
+[简体中文](README_CN.md) | English
+
+# PaddleRS Documentation

docs/README_en.md

@@ -1 +0,0 @@
-# PaddleRS Document

docs/apis/data.md → docs/apis/data_cn.md

@@ -1,3 +1,5 @@
+简体中文 | [English](data_en.md)
+
 # 数据相关API说明
 
 ## 数据集

docs/apis/data_en.md

@@ -1,3 +1,5 @@
+[简体中文](data_cn.md) | English
+
 # Data Related API Description
 
 ## Dataset

docs/apis/infer.md → docs/apis/infer_cn.md

@@ -1,3 +1,5 @@
+简体中文 | [English](infer_en.md)
+
 # PaddleRS推理API说明
 
 PaddleRS的动态图推理和静态图推理能力分别由训练器（[`BaseModel`](https://github.com/PaddlePaddle/PaddleRS/blob/develop/paddlers/tasks/base.py)及其子类）和**预测器**（`paddlers.deploy.Predictor`）提供。

docs/apis/infer_en.md

@@ -1,3 +1,5 @@
+[简体中文](infer_cn.md) | English
+
 # PaddleRS Inference API Description
 
 The dynamic graph inference and static graph inference of PaddleRS are provided by the trainer ([`BaseModel`](https://github.com/PaddlePaddle/PaddleRS/blob/develop/paddlers/tasks/base.py) and subclasses) and **predictor** (`paddlers.deploy.Predictor`) respectively.

docs/apis/train.md → docs/apis/train_cn.md

@@ -1,6 +1,8 @@
+简体中文 | [English](train_en.md)
+
 # PaddleRS训练API说明
 
-**训练器**封装了模型训练、验证、量化以及动态图推理等逻辑，定义在`paddlers/tasks/`目录下的文件中。为了方便用户使用，PaddleRS为所有支持的模型均提供了继承自父类[`BaseModel`](https://github.com/PaddlePaddle/PaddleRS/blob/develop/paddlers/tasks/base.py)的训练器，并对外提供数个API。变化检测、场景分类、目标检测、图像复原以及图像分割任务对应的训练器类型分别为`BaseChangeDetector`、`BaseClassifier`、`BaseDetector`、`BaseRestorer`和`BaseSegmenter`。本文档介绍训练器的初始化函数以及`train()`、`evaluate()` API。
+**训练器**（或模型训练器）封装了模型训练、验证、量化以及动态图推理等逻辑，定义在`paddlers/tasks/`目录下的文件中。为了方便用户使用，PaddleRS为所有支持的模型均提供了继承自父类[`BaseModel`](https://github.com/PaddlePaddle/PaddleRS/blob/develop/paddlers/tasks/base.py)的训练器，并对外提供数个API。变化检测、场景分类、目标检测、图像复原以及图像分割任务对应的训练器类型分别为`BaseChangeDetector`、`BaseClassifier`、`BaseDetector`、`BaseRestorer`和`BaseSegmenter`。本文档介绍训练器的初始化函数以及`train()`、`evaluate()` API。
 
 ## 初始化训练器
 

docs/apis/train_en.md

@@ -1,6 +1,8 @@
+[简体中文](train_cn.md) | English
+
 # PaddleRS Training API Description
 
-**Trainer** encapsulates model training, validation, quantization, and dynamic graph inference, defined in files of `paddlers/tasks/` directory. For user convenience, PaddleRS provides trainers that inherits from the parent class [`BaseModel`](https://github.com/PaddlePaddle/PaddleRS/blob/develop/paddlers/tasks/base.py) for all supported models, and provides several apis externally. The types of trainers corresponding to change detection, scene classification, target detection, image restoration and image segmentation tasks are respectively `BaseChangeDetector`、`BaseClassifier`、`BaseDetector`、`BaseRestorer` and `BaseSegmenter`。This document describes the initialization function of the trainer and `train()`、`evaluate()` API。
+**Trainers** (or model trainers) encapsulate model training, validation, quantization, and dynamic graph inference, defined in files of `paddlers/tasks/` directory. For user convenience, PaddleRS provides trainers that inherits from the parent class [`BaseModel`](https://github.com/PaddlePaddle/PaddleRS/blob/develop/paddlers/tasks/base.py) for all supported models, and provides several apis externally. The types of trainers corresponding to change detection, scene classification, target detection, image restoration and image segmentation tasks are respectively `BaseChangeDetector`、`BaseClassifier`、`BaseDetector`、`BaseRestorer` and `BaseSegmenter`。This document describes the initialization function of the trainer and `train()`、`evaluate()` API。
 
 ## Initialize the Trainer
 

docs/data/coco_tools.md → docs/data/coco_tools_cn.md

@@ -1,3 +1,5 @@
+简体中文 | [English](coco_tools_en.md)
+
 # coco_tools使用说明
 
 ## 1 工具说明

docs/data/coco_tools_en.md

@@ -1,3 +1,5 @@
+[简体中文](coco_tools_cn.md) | English
+
 # coco_tools Instructions
 
 ## 1 Tool Description

docs/data/dataset.md → docs/data/dataset_cn.md

@@ -1,3 +1,5 @@
+简体中文 | [English](dataset_en.md)
+
 # 遥感开源数据集
 
 PaddleRS搜集汇总了遥感领域常用的**开源**深度学习数据集，提供每个数据集的以下信息：数据集说明，影像信息，标注信息，源地址，AI Studio备份链接。这些数据集按任务类型可分为**图像分类、图像分割、变化检测、目标检测、目标跟踪、多标签分类、图像生成**等多种类型。目前已收录的遥感数据集有：
@@ -12,7 +14,7 @@ PaddleRS搜集汇总了遥感领域常用的**开源**深度学习数据集，
 * 图像标题数据集3个；
 * 图像生成数据集8个。
 
-欢迎访问[遥感数据集汇总](./dataset_summary.md)，以获取详细信息。
+欢迎访问[遥感数据集汇总](./dataset_summary_cn.md)，以获取详细信息。
 
 ## 特别贡献数据集
 

docs/data/dataset_en.md

@@ -1,3 +1,5 @@
+[简体中文](dataset_cn.md) | English
+
 # Remote Sensing Open Source Dataset
 
 PaddleRS has collected and summarized the most commonly used **open source** deep learning data sets in the field of remote sensing, providing the following information for each data set: dataset description, image information, annotation information, source address, and AI Studio backup link. According to the task type, these data sets can be divided into **image classification, image segmentation, change detection, object detection, object tracking, multi-label classification, image generation** and other types. Currently, the collected remote sensing datasets include:
@@ -12,7 +14,7 @@ PaddleRS has collected and summarized the most commonly used **open source** dee
 * 3 image caption datasets;
 * 8 image generation datasets.
 
-Visit [Remote Sensing Data Set Summary](./dataset_summary.md) for more information.
+Visit [Remote Sensing Data Set Summary](./dataset_summary_en.md) for more information.
 
 ## Dataset of Special Contribution
 

docs/data/dataset_summary.md → docs/data/dataset_summary_cn.md

@@ -1,3 +1,5 @@
+简体中文 | [English](dataset_summary_en.md)
+
 | <span style="white-space:nowrap;">序号<br>(aistudio<br>链接)</span> | <span style="white-space:nowrap;">&emsp;数据集名称&emsp;<br>(源链接)</span>| <span style="white-space:nowrap;">任务类型</span> | <span style="white-space:nowarp;">影像尺寸</span> | <span style="white-space:nowrap;">影像<br>通道</span> | <span style="white-space:nowrap;">影像<br>数量</span> | <span style="white-space:nowrap;">标注<br>类别</span> | <span style="white-space:nowrap;">影像<br>格式</span> | <span style="white-space:nowrap;">标注<br>格式</span>  | <span style="white-space:nowrap;">空间<br>分辨率</span> | <span style="white-space:nowrap;">光谱<br>分辨率&emsp;</span> | <span style="white-space:nowrap;">影像类型</span> | <span style="white-space:nowrap;">影像来源</span> | <span style="white-space:nowrap;">发布时间</span> | <span style="white-space:nowrap;">发布机构</span> | <span style="white-space:nowrap;">源地址</span> | <span style="white-space:nowrap;">aistudio地址</span> |
 | ------------------------------------------------------------ | ------------------------------------------------------------ | ---------- | -------------------------------------- | --------- | -------- | ------ | -------- | --------------- | ------------------ | ------------ | ------------------ | ---------------------------------------------------- | -------- | --------------------------------------------------------- | ------------------------------------------------------------ | -------------------------------------------------------- |
 | [1-1](https://aistudio.baidu.com/aistudio/datasetdetail/51628) | [UCMerced   LandUse](http://weegee.vision.ucmerced.edu/datasets/landuse.html) | 图像分类   | 256 * 256                              | 3         | 2100     | 21     | tif      | folder name     | 0.3m               | __           | 卫星影像           | USGS National Map                                    | 2010     | University of California, Merced                          | http://weegee.vision.ucmerced.edu/datasets/landuse.html      | https://aistudio.baidu.com/aistudio/datasetdetail/51628  |

docs/data/dataset_summary_en.md

@@ -1,3 +1,5 @@
+[简体中文](dataset_summary_cn.md) | English
+
 | <span style="white-space:nowrap;">Index<br>(aistudio<br>link)</span> | <span style="white-space:nowrap;">&emsp;Dataset Name&emsp;<br>(source link)</span>| <span style="white-space:nowrap;">Task Type</span> | <span style="white-space:nowarp;">Image Size</span> | <span style="white-space:nowrap;">Image<br>Channels</span> | <span style="white-space:nowrap;">Image<br>Number</span> | <span style="white-space:nowrap;">Label<br>Category</span> | <span style="white-space:nowrap;">Image<br>Format</span> | <span style="white-space:nowrap;">Label<br>Format</span>  | <span style="white-space:nowrap;">Spatial<br>Resolution</span> | <span style="white-space:nowrap;">Spectral<br>Resolution&emsp;</span> | <span style="white-space:nowrap;">Image Type</span> | <span style="white-space:nowrap;">Image Source</span> | <span style="white-space:nowrap;">Release Time</span> | <span style="white-space:nowrap;">Release Agency</span> | <span style="white-space:nowrap;">Source Link</span> | <span style="white-space:nowrap;">Aistudio Link</span> |
 | ------------------------------------------------------------ | ------------------------------------------------------------ | ---------- | -------------------------------------- | --------- | -------- | ------ | -------- | --------------- | ------------------ | ------------ | ------------------ | ---------------------------------------------------- | -------- | --------------------------------------------------------- | ------------------------------------------------------------ | -------------------------------------------------------- |
 | [1-1](https://aistudio.baidu.com/aistudio/datasetdetail/51628) | [UCMerced   LandUse](http://weegee.vision.ucmerced.edu/datasets/landuse.html) | Image Classification   | 256 * 256                              | 3         | 2100     | 21     | tif      | folder name     | 0.3m               | __           | Satellite image           | USGS National Map                                    | 2010     | University of California, Merced                          | http://weegee.vision.ucmerced.edu/datasets/landuse.html      | https://aistudio.baidu.com/aistudio/datasetdetail/51628  |

docs/data/rs_data.md → docs/data/rs_data_cn.md

@@ -1,3 +1,5 @@
+简体中文 | [English](rs_data_en.md)
+
 # 遥感数据介绍
 
 ## 1 遥感与遥感影像的定义

docs/data/rs_data_en.md

@@ -1,3 +1,5 @@
+[简体中文](rs_data_cn.md) | English
+
 # Introduction to Remote Sensing Data
 
 ## 1 Definition of Remote Sensing and Remote Sensing Images

docs/data/tools.md → docs/data/tools_cn.md

@@ -1,3 +1,5 @@
+简体中文 | [English](tools_en.md)
+
 # 遥感影像处理工具集
 
 PaddleRS在`tools`目录中提供了丰富的遥感影像处理工具，包括：
@@ -103,7 +105,7 @@ python split.py --image_path {输入影像路径} [--mask_path {真值标签路
 - `json_Split.py`：       将json文件中的内容划分为train set和val set；
 - `json_Merge.py`：       将多个json文件合并为一个。
 
-详细使用方法请参见[coco_tools使用说明](coco_tools.md)。
+详细使用方法请参见[coco_tools使用说明](coco_tools_cn.md)。
 
 ### prepare_dataset
 
@@ -124,7 +126,7 @@ python prepare_dataset/prepare_levircd.py --help
 - `--seed`：随机种子。可用于固定随机数生成器产生的伪随机数序列，从而得到固定的数据集划分结果。示例：`--seed 1919810`
 - `--ratios`：对于支持子集随机划分的数据集，指定需要划分的各个子集的样本比例。示例：`--ratios 0.7 0.2 0.1`。
 
-您可以在[此文档](https://github.com/PaddlePaddle/PaddleRS/blob/develop/docs/intro/data_prep.md)中查看PaddleRS提供哪些数据集的预处理脚本。
+您可以在[此文档](https://github.com/PaddlePaddle/PaddleRS/blob/develop/docs/intro/data_prep_cn.md)中查看PaddleRS提供哪些数据集的预处理脚本。
 
 ### extract_ms_patches
 

docs/data/tools_en.md

@@ -1,3 +1,5 @@
+[简体中文](tools_cn.md) | English
+
 # Remote Sensing Image Processing Toolkit
 
 PaddleRS provides a rich set of remote sensing image processing tools in the `tools` directory, including:
@@ -103,7 +105,7 @@ There are six tools included in the `coco_tools` directory, each with the follow
 - `json_Split.py`:       Split the content of a json file into train set and val set.
 - `json_Merge.py`:       Merge multiple json files into one.
 
-For detailed usage instructions, please refer to [coco_tools Usage Instructions](coco_tools.md).
+For detailed usage instructions, please refer to [coco_tools Usage Instructions](coco_tools_en.md).
 
 ### prepare_dataset
 
@@ -124,7 +126,7 @@ The following are common command-line options in the script:
 - `--seed`: Random seed. It can be used to fix the pseudo-random number sequence generated by the random number generator, so as to obtain a fixed dataset partitioning result. Example: `--seed 1919810`
 - `--ratios`: For datasets that support random subset partitioning, specify the sample ratios of each subset that needs to be partitioned. Example: `--ratios 0.7 0.2 0.1`.
 
-You can refer to [this document](https://github.com/PaddlePaddle/PaddleRS/blob/develop/docs/intro/data_prep.md) to see which preprocessing scripts for datasets are provided by PaddleRS.
+You can refer to [this document](https://github.com/PaddlePaddle/PaddleRS/blob/develop/docs/intro/data_prep_en.md) to see which preprocessing scripts for datasets are provided by PaddleRS.
 
 ### extract_ms_patches
 

docs/dev/dev_guide.md → docs/dev/dev_guide_cn.md

@@ -1,3 +1,5 @@
+简体中文 | [English](dev_guide_en.md)
+
 # PaddleRS开发指南
 
 ## 0 目录
@@ -31,7 +33,7 @@
 
 ### 1.2 添加docstring
 
-必须为新模型添加docstring，并在其中给出原文引用和链接（对引用格式不做严格要求，但希望尽可能和该任务已有的其他模型保持一致）。详细的注释规范请参考[《代码注释规范》](docstring.md)。一个例子如下所示：
+必须为新模型添加docstring，并在其中给出原文引用和链接（对引用格式不做严格要求，但希望尽可能和该任务已有的其他模型保持一致）。详细的注释规范请参考[《代码注释规范》](docstring_cn.md)。一个例子如下所示：
 
 ```python
 """

docs/dev/dev_guide_en.md

@@ -1,14 +1,16 @@
+[简体中文](dev_guide_cn.md) | English
+
 # PaddleRS Development Guide
 
 ## 0 Catalog
 
-- [Add Remote Sensing Special Model](#1-add-remote-sensing-special-model)
+- [Add Remote Sensing Dedicated Model](#1-add-remote-sensing-dedicated-models)
 
-- [Add Data Preprocessing/Data Augmentation Function or Operator](#2-add-data-preprocessing/data-augmentation-function-or-operator)
+- [Add Data Preprocessing/Data Augmentation Function or Operator](#2-add-data-preprocessing/data-augmentation-functions-or-operators)
 
 - [Add Remote Sensing Image Processing Tools](#3-add-remote-sensing-image-processing-tools)
 
-## 1 Add Remote Sensing Special Model
+## 1 Add Remote Sensing Dedicated Models
 
 ### 1.1 Write Model Definitions
 
@@ -29,9 +31,9 @@ The new model must be a subclass of `paddle.nn.Layer`. For the tasks of image se
 
 Note that if a common component exists in a subdirectory. For example, contents in `paddlers/rs_models/cd/layers`, `paddlers/rs_models/cd/backbones` and `paddlers/rs_models/seg/layers` should be reused as much as possible.
 
-### 1.2 Add docstring
+### 1.2 Add Docstrings
 
-You have to add a docstring to the new model, with the original references and links in it (you don't have to be strict about the reference format, but you want to be as consistent as possible with the other models you already have for the task). For detailed annotation specifications, refer to the [Code Annotation Specification](docstring.md). An example is as follows:
+You have to add a docstring to the new model, with the original references and links in it (you don't have to be strict about the reference format, but you want to be as consistent as possible with the other models you already have for the task). For detailed annotation specifications, refer to the [Code Annotation Specification](docstring_en.md). An example is as follows:
 
 ```python
 """
@@ -79,7 +81,7 @@ It should be noted that for the image restoration task, the forward and backward
 
 See `ESRGAN` for specific examples of GAN trainers.
 
-## 2 Add Data Preprocessing/Data Augmentation Function or Operator
+## 2 Add Data Preprocessing/Data Augmentation Functions or Operators
 
 ### 2.1 Add Data Preprocessing/Data Augmentation Functions
 

docs/dev/docstring.md → docs/dev/docstring_cn.md

@@ -1,3 +1,5 @@
+简体中文 | [English](docstring_en.md)
+
 # PaddleRS代码注释规范
 
 ## 1 注释规范

docs/dev/docstring_en.md

@@ -1,3 +1,5 @@
+[简体中文](docstring_cn.md) | English
+
 # PaddleRS Specification for Code Annotation
 
 ## 1 Specification for Docstrings
@@ -112,7 +114,7 @@ Example:
 """
 ```
 
-### 1.5 Usage Example
+### 1.5 Example on Usage
 
 Provide as many examples as possible for various usage scenarios of the function or class, and give the expected results of executing the code in the comments.
 
@@ -143,7 +145,7 @@ Single example:
 """
 ```
 
-Multi examples:
+Multi-examples:
 
 ```python
 """
@@ -184,8 +186,8 @@ Multi examples:
 
 ### 1.6 Grammar
 
-- Wording is accurate, using vocabulary and expressions common in deep learning.
-- The sentences are smooth and in line with English grammar.
+- Wording should be accurate, using vocabulary and expressions common in deep learning.
+- The sentences should be smooth and in line with English grammar.
 - The document should be consistent in the expression of the same thing, for example, avoid using label sometimes and ground truth sometimes.
 
 ### 1.7 Other Points to Note

docs/intro/data_prep.md → docs/intro/data_prep_cn.md

@@ -1,3 +1,5 @@
+简体中文 | [English](data_prep_en.md)
+
 # 数据集预处理脚本
 
 ## PaddleRS已支持的数据集预处理脚本列表

docs/intro/data_prep_en.md

@@ -1,3 +1,5 @@
+[简体中文](data_prep_cn.md) | English
+
 # Dataset Preprocessing Scripts
 
 ## List of PaddleRS Supported Data Set Preprocessing Scripts

docs/intro/indices.md → docs/intro/indices_cn.md

@@ -1,3 +1,5 @@
+简体中文 | [English](indices_en.md)
+
 # 遥感指数
 
 通过`paddlers.transforms.AppendIndex`算子可以计算遥感指数并追加到输入影像的最后一个波段。在构建`AppendIndex`对象时，需要传入遥感指数名称以及一个包含波段-索引对应关系的字典（字典中的键为波段名称，索引号从1开始计数）。

docs/intro/indices_en.md

@@ -1,6 +1,8 @@
-# Remote Sensing Index
+[简体中文](indices_cn.md) | English
 
-Through `paddlers.transforms.AppendIndex` operator remote sensing index can be calculated and appended to the input image of the last band. When you build the `AppendIndex` object, you need to pass in the remote sensing index name and a dictionary containing the band-index correspondence (the key in the dictionary is the band name and the index number counts from 1).
+# Remote Sensing Indices
+
+Through `paddlers.transforms.AppendIndex` operator remote sensing index can be calculated and appended to the input image in the last band. When you build the `AppendIndex` object, you need to pass in the remote sensing index name and a dictionary containing the band-index correspondence (the key in the dictionary is the band name and the index number counts from 1).
 
 ## List of PaddleRS Supported Remote Sensing Indices
 

docs/intro/model_cons_param_cn.md → docs/intro/model_cons_params_cn.md

@@ -1,3 +1,5 @@
+简体中文 | [English](model_cons_params_en.md)
+
 # PaddleRS模型构造参数
 
 本文档详细介绍了PaddleRS各个模型训练器的构造参数，包括其参数名、参数类型、参数描述及默认值。

docs/intro/model_cons_param_en.md → docs/intro/model_cons_params_en.md

@@ -1,3 +1,5 @@
+[简体中文](model_cons_param_cn.md) | English
+
 # PaddleRS Model Construction Parameters
 
 This document describes the construction parameters of each PaddleRS model trainer in detail, including their parameter names, parameter types, parameter descriptions and default values.

docs/intro/model_zoo.md → docs/intro/model_zoo_cn.md

@@ -1,3 +1,5 @@
+简体中文 | [English](model_zoo_en.md)
+
 # 模型库
 
 PaddleRS的基础模型库来自Paddle-CV系列套件：[PaddleClas](https://github.com/PaddlePaddle/PaddleClas/blob/release/2.3/docs/zh_CN/algorithm_introduction/ImageNet_models.md)、[PaddleSeg](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.4/docs/model_zoo_overview_cn.md)、[PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.3/README_cn.md#模型库)以及[PaddleGAN](https://github.com/PaddlePaddle/PaddleGAN/blob/develop/README_cn.md#模型库)。除此之外，PaddleRS也包含一系列遥感特色模型，可用于遥感影像分割、变化检测等。
@@ -40,3 +42,7 @@ PaddleRS目前已支持的全部模型如下（标注\*的为遥感专用模型
 | 图像分割 | Fast-SCNN | 是 |
 | 图像分割 | HRNet | 是 |
 | 图像分割 | UNet | 是 |
+
+## 构造模型训练器
+
+参见[此文档](model_cons_params_cn.md)。

docs/intro/model_zoo_en.md

@@ -1,12 +1,14 @@
+[简体中文](model_zoo_cn.md) | English
+
 # Model Zoo
 
-PaddleRS' base model library comes from the PaddleCV development kits: [PaddleClas](https://github.com/PaddlePaddle/PaddleClas/blob/release/2.3/docs/en/algorithm_introduction/ImageNet_models_en.md), [PaddleSeg](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.4/docs/model_zoo_overview.md), [PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.3/README_en.md) and [PaddleGAN](https://github.com/PaddlePaddle/PaddleGAN/blob/develop/README.md). In addition, PaddleRS also contains a series of remote sensing feature models, which can be used for remote sensing image segmentation and change detection.
+PaddleRS' base model library originates from the PaddleCV development kits: [PaddleClas](https://github.com/PaddlePaddle/PaddleClas/blob/release/2.3/docs/en/algorithm_introduction/ImageNet_models_en.md), [PaddleSeg](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.4/docs/model_zoo_overview.md), [PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.3/README_en.md) and [PaddleGAN](https://github.com/PaddlePaddle/PaddleGAN/blob/develop/README.md). In addition, PaddleRS also contains a series of models specially designed for remote sensing tasks, which can be used for remote sensing image segmentation, change detection, etc.
 
 ## List of PaddleRS Supported Models
 
-All models currently supported by PaddleRS are as follows (those marked \* are dedicated models for remote sensing) :
+All models currently supported by PaddleRS are listed below (those marked \* are dedicated models for remote sensing) :
 
-| Task | Model | Multiband Support |
+| Task | Model | Multi-band Support |
 |--------|---------|------|
 | Change Detection | \*BIT | Yes |
 | Change Detection | \*CDNet | Yes |
@@ -40,3 +42,7 @@ All models currently supported by PaddleRS are as follows (those marked \* are d
 | Image Segmentation | Fast-SCNN | Yes |
 | Image Segmentation | HRNet | Yes |
 | Image Segmentation | UNet | Yes |
+
+## Model Trainer Construction
+
+See [this document](model_cons_params_en.md).

docs/intro/transforms.md → docs/intro/transforms_cn.md

@@ -1,3 +1,5 @@
+简体中文 | [English](transforms_en.md)
+
 # 数据变换算子
 
 ## PaddleRS已支持的数据变换算子列表
@@ -32,4 +34,8 @@ PaddleRS对不同遥感任务需要的数据预处理/数据增强（合称为
 
 ## 组合算子
 
-在实际的模型训练过程中，常常需要组合多种数据预处理与数据增强策略。PaddleRS提供了`paddlers.transforms.Compose`以便捷地组合多个数据变换算子，使这些算子能够串行执行。关于`paddlers.transforms.Compose`的具体用法请参见[API说明](https://github.com/PaddlePaddle/PaddleRS/blob/develop/docs/apis/data.md)。
+在实际的模型训练过程中，常常需要组合多种数据预处理与数据增强策略。PaddleRS提供了`paddlers.transforms.Compose`以便捷地组合多个数据变换算子，使这些算子能够串行执行。关于`paddlers.transforms.Compose`的具体用法请参见[API说明](https://github.com/PaddlePaddle/PaddleRS/blob/develop/docs/apis/data_cn.md)。
+
+## 构造算子
+
+参见[此文档](transforms_cons_params_cn.md)。

docs/intro/transforms_cons_params_cn.md

@@ -1,8 +1,10 @@
+简体中文 | [English](transforms_cons_params_en.md)
+
 # PaddleRS数据变换算子构造参数
 
-本文档详细介绍了PaddleRS各个数据变化算子的构造参数，包括算子名称、算子用途、各个算子的参数名称、参数类型、参数意义以及参数默认值。
+本文档详细介绍了PaddleRS各个数据变换算子的构造参数，包括算子名称、算子用途、各个算子的参数名称、参数类型、参数意义以及参数默认值。
 
-PaddleRS所支持的数据变换算子可见(https://github.com/PaddlePaddle/PaddleRS/blob/develop/docs/intro/transforms.md)
+PaddleRS所支持的数据变换算子可见[此文档](https://github.com/PaddlePaddle/PaddleRS/blob/develop/docs/intro/transforms_cn.md)。
 
 ## `AppendIndex`
 

docs/intro/transforms_cons_params_en.md

@@ -1,7 +1,11 @@
+[简体中文](transforms_cons_params_cn.md) | English
+
 # PaddleRS Data Transformation Operator Construction Parameters
 
 This document describes the parameters of each PaddleRS data transformation operator in detail, including the operator name, operator purpose, parameter name, parameter type, parameter meaning, and parameter default value of each operator.
 
+You can check all data transformation operators supported by PaddleRS [here](https://github.com/PaddlePaddle/PaddleRS/blob/develop/docs/intro/transforms_en.md).
+
 ## `AppendIndex`
 
 Append remote sensing index to input image(s).

docs/intro/transforms_en.md

@@ -1,10 +1,12 @@
+[简体中文](transforms_cn.md) | English
+
 # Data Transformation Operator
 
 ## List of PaddleRS Supported Data Transformation Operators
 
-PaddleRS has organically integrated the data preprocessing/data augmentation (collectively called data transformation) strategies required by different remote sensing tasks, and designed a unified operator. Considering the multi-band characteristics of remote sensing images, most data processing operators of PaddleRS can process input of any number of bands. All data transformation operators currently provided by PaddleRS are listed as follows:
+PaddleRS has organically integrated the data preprocessing/data augmentation (collectively called data transformation) strategies required by different remote sensing tasks, and designed a unified operator. Considering the multi-band characteristics of remote sensing images, most data transformation operators of PaddleRS can process input of any number of bands. All data transformation operators currently provided by PaddleRS are listed as follows:
 
-| The name of the data transformation operator | Purpose                                                     | Task     | ... |
+| Name | Purpose                                                     | Task     | ... |
 | -------------------- | ------------------------------------------------- | -------- | ---- |
 | AppendIndex          | Calculate the remote sensing index and add it to the input image. | All tasks  | ... |  
 | CenterCrop           | Perform center cropping on the input image. | All tasks | ... |
@@ -32,4 +34,8 @@ PaddleRS has organically integrated the data preprocessing/data augmentation (co
 
 ## Combinatorial Operator
 
-In the actual model training process, it is often necessary to combine a variety of data preprocessing and data augmentation strategies. PaddleRS provides `paddlers.transforms.Compose` to easily combine multiple data transformation operators so that they can be executed serially. For the specific usage of the `paddlers.transforms.Compose` please see [API Description](https://github.com/PaddlePaddle/PaddleRS/blob/develop/docs/apis/data.md).
+During the model training process, it is often necessary to combine a variety of data preprocessing and data augmentation strategies. PaddleRS provides `paddlers.transforms.Compose` to easily combine multiple data transformation operators so that they can be executed serially. For the specific usage of the `paddlers.transforms.Compose` please see [API Description](https://github.com/PaddlePaddle/PaddleRS/blob/develop/docs/apis/data_en.md).
+
+## Operator Construction
+
+See [this document](transforms_cons_params_en.md).

docs/quick_start.md

@@ -1,46 +0,0 @@
-# 快速开始
-
-## 环境准备
-
-环境准备可参考：[使用教程——训练模型](../tutorials/train/README.md)
-
-## 模型训练
-
-+ 在安装完成PaddleRS后，即可开始模型训练。
-+ 模型训练可参考：[使用教程——训练模型](../tutorials/train/README.md)
-
-## 模型精度验证
-
-模型训练完成后，需要对模型进行精度验证，以确保模型的预测效果符合预期。以DeepLab V3+图像分割模型为例，可以使用以下命令启动：
-
-```python
-import paddlex as pdx
-
-# 加载模型
-model = pdx.load_model('output/deeplabv3p/best_model')
-
-# 加载验证集
-dataset = pdx.datasets.SegDataset(
-    data_dir='dataset/val',
-    file_list='dataset/val/list.txt',
-    label_list='dataset/labels.txt',
-    transforms=model.eval_transforms)
-
-# 进行验证
-result = model.evaluate(dataset, batch_size=1, epoch_id=None, return_details=True)
-
-print(result)
-```
-
-在上述代码中，`pdx.load_model()`方法用于加载预训练的DeepLabV3P模型，`pdx.datasets.SegDataset()`方法用于加载验证集数据。`model.evaluate()`方法接受验证集数据集、批大小和轮数等参数，并返回包括预测结果和指标评估在内的验证结果。最后，我们可以打印输出验证结果。
-
-
-## 模型部署
-
-### 模型导出
-
-模型导出可参考：[部署模型导出](../deploy/export/README.md)
-
-### Python部署
-
-Python部署可参考：[Python部署](../deploy/README.md)

docs/quick_start_cn.md

@@ -0,0 +1,126 @@
+简体中文 | [English](quick_start_en.md)
+
+# 快速开始
+
+## 环境准备
+
+1. [安装PaddlePaddle](https://www.paddlepaddle.org.cn/install/quick)
+  - 版本要求：PaddlePaddle>=2.2.0
+
+2. 安装PaddleRS
+
+如果希望获取更加稳定的体验，请下载安装[PaddleRS发行版](https://github.com/PaddlePaddle/PaddleRS/releases)。
+
+```shell
+pip install -r requirements.txt
+pip install .
+```
+
+PaddleRS代码会跟随开发进度不断更新，如果希望使用最新功能，请安装PaddleRS develop分支。安装方式如下：
+
+```shell
+git clone https://github.com/PaddlePaddle/PaddleRS
+cd PaddleRS
+git checkout develop
+pip install -r requirements.txt
+pip install .
+```
+
+若在执行`pip install .`时下载依赖缓慢或超时，可以在`setup.py`相同目录下新建`setup.cfg`，并输入以下内容，则可通过清华源进行加速下载：
+
+```
+[easy_install]
+index-url=https://pypi.tuna.tsinghua.edu.cn/simple
+```
+
+3. （可选）安装GDAL
+
+PaddleRS支持对多种类型卫星数据的读取。完整使用PaddleRS的遥感数据读取功能需要安装GDAL，安装方式如下：
+
+  - Linux / MacOS
+
+推荐使用conda进行安装:
+
+```shell
+conda install gdal
+```
+
+  - Windows
+
+Windows用户可以在[此站点](https://www.lfd.uci.edu/~gohlke/pythonlibs/#gdal)下载与Python和系统版本相对应的.whl格式安装包到本地，以*GDAL‑3.3.3‑cp39‑cp39‑win_amd64.whl*为例，使用pip工具安装:
+
+```shell
+pip install GDAL‑3.3.3‑cp39‑cp39‑win_amd64.whl
+```
+
+除了采用上述安装步骤以外，PaddleRS也提供Docker安装方式。具体步骤如下：
+
+1. 从dockerhub拉取镜像:
+
+```shell
+docker pull paddlepaddle/paddlers:1.0.0  # 暂无
+```
+
+或者，可以选择从头开始构建。通过修改`Dockerfile`文件中的`PPTAG`，可选择PaddlePaddle的多种基础镜像。
+
+```shell
+git clone https://github.com/PaddlePaddle/PaddleRS
+cd PaddleRS
+docker build -t <imageName> .  # 默认使用PaddlePaddle 2.4.1的CPU版本
+# docker build -t <imageName> . --build-arg PPTAG=2.4.1-gpu-cuda10.2-cudnn7.6-trt7.0  # 构建使用GPU版本PaddlePaddle的环境
+# 其余tag可以参考：https://hub.docker.com/r/paddlepaddle/paddle/tags
+```
+
+2. 启动容器
+
+```shell
+docker images  # 查看镜像的ID
+docker run -it <imageID>
+```
+
+## 模型训练
+
++ 在安装完成PaddleRS后，即可开始模型训练。
++ 模型训练可参考：[使用教程——训练模型](../tutorials/train/README_CN.md)
+
+## 模型精度验证
+
+模型训练完成后，需要对模型进行精度验证，以确保模型的预测效果符合预期。以DeepLab V3+图像分割模型为例，可以使用以下命令启动：
+
+```python
+import paddlers as pdrs
+from paddlers import transforms as T
+
+# 加载模型
+model = pdrs.load_model('output/deeplabv3p/best_model')
+
+# 组合数据变换算子
+eval_transforms = [
+    T.Resize(target_size=512),
+    T.Normalize(
+        mean=[0.5] * NUM_BANDS, std=[0.5] * NUM_BANDS),
+    T.ReloadMask()
+]
+
+# 加载验证集
+dataset = pdrs.datasets.SegDataset(
+    data_dir='dataset',
+    file_list='dataset/val/list.txt',
+    label_list='dataset/labels.txt',
+    transforms=eval_transforms)
+
+# 进行验证
+result = model.evaluate(dataset)
+
+print(result)
+```
+
+## 模型部署
+
+### 模型导出
+
+模型导出可参考：[部署模型导出](../deploy/export/README.md)
+
+### Python部署
+
+Python部署可参考：[Python部署](../deploy/README.md)

docs/quick_start_en.md

@@ -0,0 +1,118 @@
+[简体中文](quick_start_cn.md) | English
+
+# Quick Start
+
+## Prerequisites
+
+1. [Install PaddlePaddle](https://www.paddlepaddle.org.cn/install/quick)
+  - Version requirements: PaddlePaddle>=2.2.0
+
+2. Install PaddleRS
+
+Check out releases of PaddleRS [here](https://github.com/PaddlePaddle/PaddleRS/releases). Download and extract the source code and run:
+
+```shell
+pip install -r requirements.txt
+pip install .
+```
+
+The PaddleRS code will be updated as the development progresses. You can also install the develop branch to use the latest features as follows:
+
+```shell
+git clone https://github.com/PaddlePaddle/PaddleRS
+cd PaddleRS
+git checkout develop
+pip install -r requirements.txt
+pip install .
+```
+
+3. (Optional) Install GDAL
+
+PaddleRS supports reading of various types of satellite data. To use the full data reading functionality of PaddleRS, you need to install GDAL as follows:
+
+  - Linux / MacOS
+
+conda is recommended for installation:
+
+```shell
+conda install gdal
+```
+
+  - Windows
+
+Windows users can download GDAL wheels from [this site](https://www.lfd.uci.edu/~gohlke/pythonlibs/#gdal). Please choose the wheel according to the Python version and the platform. Take *GDAL‑3.3.3‑cp39‑cp39‑win_amd64.whl* as an example, run the following command to install:
+
+```shell
+pip install GDAL‑3.3.3‑cp39‑cp39‑win_amd64.whl
+```
+
+We also provide a docker image for installation:
+
+1. Pull from dockerhub:
+
+```shell
+docker pull paddlepaddle/paddlers:1.0.0
+```
+
+Optionally, you can build the image from scratch. You can change the base images for different PaddlePaddle versions by setting `PPTAG` in `Dockerfile`.
+
+```shell
+git clone https://github.com/PaddlePaddle/PaddleRS
+cd PaddleRS
+docker build -t <imageName> .  # Default is PaddlePaddle-2.4.1-CPU
+# docker build -t <imageName> . --build-arg PPTAG=2.4.1-gpu-cuda10.2-cudnn7.6-trt7.0  # Use a GPU version of PaddlePaddle
+# For more tags, please refer to: https://hub.docker.com/r/paddlepaddle/paddle/tags
+```
+
+2. Start a container
+
+```shell
+docker images  # View the ID of the image
+docker run -it <imageID>
+```
+
+## Model Training
+
+See [here](../tutorials/train/README_EN.md).
+
+## Model Evaluation
+
+After the model training is completed, you can evaluate the model by executing the following snippet (take DeepLab V3+ as an example):
+
+```python
+import paddlers as pdrs
+from paddlers import transforms as T
+
+# Load the trained model
+model = pdrs.load_model('output/deeplabv3p/best_model')
+
+# Combine data transformation operators
+eval_transforms = [
+    T.Resize(target_size=512),
+    T.Normalize(
+        mean=[0.5] * NUM_BANDS, std=[0.5] * NUM_BANDS),
+    T.ReloadMask()
+]
+
+# Load the validation dataset
+dataset = pdrs.datasets.SegDataset(
+    data_dir='dataset',
+    file_list='dataset/val/list.txt',
+    label_list='dataset/labels.txt',
+    transforms=eval_transforms)
+
+# Do the evaluation
+result = model.evaluate(dataset)
+
+print(result)
+```
+
+## Model Deployment
+
+### Model Exporting
+
+Please refer to [this document](../deploy/export/README.md).
+
+### Deployment Using Python
+
+Please refer to [this document](../deploy/README.md).

tutorials/train/README.md

@@ -1,133 +0,0 @@
-# 使用教程——训练模型
-
-本目录中整理了使用PaddleRS训练模型的示例代码。代码中均提供对示例数据的自动下载，并均使用GPU对模型进行训练。
-
-|示例代码路径 | 任务 | 模型 |
-|------|--------|---------|
-|change_detection/bit.py | 变化检测 | BIT |
-|change_detection/cdnet.py | 变化检测 | CDNet |
-|change_detection/changeformer.py | 变化检测 | ChangeFormer |
-|change_detection/dsamnet.py | 变化检测 | DSAMNet |
-|change_detection/dsifn.py | 变化检测 | DSIFN |
-|change_detection/fc_ef.py | 变化检测 | FC-EF |
-|change_detection/fc_siam_conc.py | 变化检测 | FC-Siam-conc |
-|change_detection/fc_siam_diff.py | 变化检测 | FC-Siam-diff |
-|change_detection/fccdn.py | 变化检测 | FCCDN |
-|change_detection/p2v.py | 变化检测 | P2V-CD |
-|change_detection/snunet.py | 变化检测 | SNUNet |
-|change_detection/stanet.py | 变化检测 | STANet |
-|classification/condensenetv2.py | 场景分类 | CondenseNet V2 |
-|classification/hrnet.py | 场景分类 | HRNet |
-|classification/mobilenetv3.py | 场景分类 | MobileNetV3 |
-|classification/resnet50_vd.py | 场景分类 | ResNet50-vd |
-|image_restoration/drn.py | 图像复原 | DRN |
-|image_restoration/esrgan.py | 图像复原 | ESRGAN |
-|image_restoration/lesrcnn.py | 图像复原 | LESRCNN |
-|object_detection/faster_rcnn.py | 目标检测 | Faster R-CNN |
-|object_detection/ppyolo.py | 目标检测 | PP-YOLO |
-|object_detection/ppyolo_tiny.py | 目标检测 | PP-YOLO Tiny |
-|object_detection/ppyolov2.py | 目标检测 | PP-YOLOv2 |
-|object_detection/yolov3.py | 目标检测 | YOLOv3 |
-|semantic_segmentation/bisenetv2.py | 图像分割 | BiSeNet V2 |
-|semantic_segmentation/deeplabv3p.py | 图像分割 | DeepLab V3+ |
-|semantic_segmentation/factseg.py | 图像分割 | FactSeg |
-|semantic_segmentation/farseg.py | 图像分割 | FarSeg |
-|semantic_segmentation/fast_scnn.py | 图像分割 | Fast-SCNN |
-|semantic_segmentation/hrnet.py | 图像分割 | HRNet |
-|semantic_segmentation/unet.py | 图像分割 | UNet |
-
-## 环境准备
-
-+ [PaddlePaddle安装](https://www.paddlepaddle.org.cn/install/quick)
-  - 版本要求：PaddlePaddle>=2.2.0
-
-+ PaddleRS安装
-
-PaddleRS代码会跟随开发进度不断更新，可以安装develop分支的代码使用最新的功能，安装方式如下：
-
-```shell
-git clone https://github.com/PaddlePaddle/PaddleRS
-cd PaddleRS
-git checkout develop
-pip install -r requirements.txt
-python setup.py install
-```
-
-若在使用`python setup.py install`时下载依赖缓慢或超时，可以在`setup.py`相同目录下新建`setup.cfg`，并输入以下内容，则可通过清华源进行加速下载：
-
-```
-[easy_install]
-index-url=https://pypi.tuna.tsinghua.edu.cn/simple
-```
-
-+ （可选）GDAL安装
-
-PaddleRS支持对多种类型卫星数据的读取。完整使用PaddleRS的遥感数据读取功能需要安装GDAL，安装方式如下：
-
-  - Linux / MacOS
-
-推荐使用conda进行安装:
-
-```shell
-conda install gdal
-```
-
-  - Windows
-
-Windows用户可以在[此站点](https://www.lfd.uci.edu/~gohlke/pythonlibs/#gdal)下载与Python和系统版本相对应的.whl格式安装包到本地，以*GDAL‑3.3.3‑cp39‑cp39‑win_amd64.whl*为例，使用pip工具安装:
-
-```shell
-pip install GDAL‑3.3.3‑cp39‑cp39‑win_amd64.whl
-```
-
-### *Docker安装
-
-1. 从dockerhub拉取:
-
-```shell
-docker pull paddlepaddle/paddlers:1.0.0  # 暂无
-```
-
-- （可选）从头开始构建，可以通过设置`PPTAG`选择PaddlePaddle的多种基础镜像，构建CPU或不同GPU环境:
-
-```shell
-git clone https://github.com/PaddlePaddle/PaddleRS
-cd PaddleRS
-docker build -t <imageName> .  # 默认为2.4.1的cpu版本
-# docker build -t <imageName> . --build-arg PPTAG=2.4.1-gpu-cuda10.2-cudnn7.6-trt7.0  # 2.4.1的gpu版本之一
-# 其余Tag可以参考：https://hub.docker.com/r/paddlepaddle/paddle/tags
-```
-
-2. 启动容器
-
-```shell
-docker images  # 查看镜像的ID
-docker run -it <imageID>
-```
-
-## 开始训练
-
-+ 在安装完成PaddleRS后，使用如下命令执行单卡训练。脚本将自动下载训练数据。以DeepLab V3+图像分割模型为例：
-
-```shell
-# 指定需要使用的GPU设备编号
-export CUDA_VISIBLE_DEVICES=0
-python tutorials/train/semantic_segmentation/deeplabv3p.py
-```
-
-+ 如需使用多块GPU进行训练，例如使用2张显卡时，执行如下命令：
-
-```shell
-python -m paddle.distributed.launch --gpus 0,1 tutorials/train/semantic_segmentation/deeplabv3p.py
-```
-
-## VisualDL可视化训练指标
-
-将传入`train()`方法的`use_vdl`参数设为`True`，则模型训练过程中将自动把训练日志以VisualDL的格式存储到`save_dir`（用户自己指定的路径）目录下名为`vdl_log`的子目录中。用户可以使用如下命令启动VisualDL服务，查看可视化指标。同样以DeepLab V3+模型为例：
-
-```shell
-# 指定端口号为8001
-visualdl --logdir output/deeplabv3p/vdl_log --port 8001
-```
-
-服务启动后，使用浏览器打开 https://0.0.0.0:8001 或 https://localhost:8001 即可进入可视化页面。

tutorials/train/README.md

@@ -0,0 +1 @@
+README_CN.md

tutorials/train/README_CN.md

@@ -0,0 +1,66 @@
+简体中文 | [English](README_EN.md)
+
+# 使用教程——训练模型
+
+本目录中整理了使用PaddleRS训练模型的示例代码。代码中均提供对示例数据的自动下载，并均使用GPU对模型进行训练。
+
+|示例代码路径 | 任务 | 模型 |
+|------|--------|---------|
+|change_detection/bit.py | 变化检测 | BIT |
+|change_detection/cdnet.py | 变化检测 | CDNet |
+|change_detection/changeformer.py | 变化检测 | ChangeFormer |
+|change_detection/dsamnet.py | 变化检测 | DSAMNet |
+|change_detection/dsifn.py | 变化检测 | DSIFN |
+|change_detection/fc_ef.py | 变化检测 | FC-EF |
+|change_detection/fc_siam_conc.py | 变化检测 | FC-Siam-conc |
+|change_detection/fc_siam_diff.py | 变化检测 | FC-Siam-diff |
+|change_detection/fccdn.py | 变化检测 | FCCDN |
+|change_detection/p2v.py | 变化检测 | P2V-CD |
+|change_detection/snunet.py | 变化检测 | SNUNet |
+|change_detection/stanet.py | 变化检测 | STANet |
+|classification/condensenetv2.py | 场景分类 | CondenseNet V2 |
+|classification/hrnet.py | 场景分类 | HRNet |
+|classification/mobilenetv3.py | 场景分类 | MobileNetV3 |
+|classification/resnet50_vd.py | 场景分类 | ResNet50-vd |
+|image_restoration/drn.py | 图像复原 | DRN |
+|image_restoration/esrgan.py | 图像复原 | ESRGAN |
+|image_restoration/lesrcnn.py | 图像复原 | LESRCNN |
+|object_detection/faster_rcnn.py | 目标检测 | Faster R-CNN |
+|object_detection/ppyolo.py | 目标检测 | PP-YOLO |
+|object_detection/ppyolo_tiny.py | 目标检测 | PP-YOLO Tiny |
+|object_detection/ppyolov2.py | 目标检测 | PP-YOLOv2 |
+|object_detection/yolov3.py | 目标检测 | YOLOv3 |
+|semantic_segmentation/bisenetv2.py | 图像分割 | BiSeNet V2 |
+|semantic_segmentation/deeplabv3p.py | 图像分割 | DeepLab V3+ |
+|semantic_segmentation/factseg.py | 图像分割 | FactSeg |
+|semantic_segmentation/farseg.py | 图像分割 | FarSeg |
+|semantic_segmentation/fast_scnn.py | 图像分割 | Fast-SCNN |
+|semantic_segmentation/hrnet.py | 图像分割 | HRNet |
+|semantic_segmentation/unet.py | 图像分割 | UNet |
+
+## 启动训练
+
++ 在安装完成PaddleRS后，使用如下命令执行单卡训练。脚本将自动下载训练数据。以DeepLab V3+图像分割模型为例：
+
+```shell
+# 指定需要使用的GPU设备编号
+export CUDA_VISIBLE_DEVICES=0
+python tutorials/train/semantic_segmentation/deeplabv3p.py
+```
+
++ 如需使用多块GPU进行训练，例如使用2张显卡时，执行如下命令：
+
+```shell
+python -m paddle.distributed.launch --gpus 0,1 tutorials/train/semantic_segmentation/deeplabv3p.py
+```
+
+## 使用VisualDL可视化训练指标
+
+将传入`train()`方法的`use_vdl`参数设为`True`，则模型训练过程中将自动把训练日志以VisualDL的格式存储到`save_dir`（用户自己指定的路径）目录下名为`vdl_log`的子目录中。用户可以使用如下命令启动VisualDL服务，查看可视化指标。同样以DeepLab V3+模型为例：
+
+```shell
+# 指定端口号为8001
+visualdl --logdir output/deeplabv3p/vdl_log --port 8001
+```
+
+服务启动后，使用浏览器打开 https://0.0.0.0:8001 或 https://localhost:8001 即可进入可视化页面。

tutorials/train/README_en.md → tutorials/train/README_EN.md

@@ -1,8 +1,10 @@
-# Tutorial - Training Model
+[简体中文](README_CN.md) | English
+
+# Tutorials - Model Training
 
 Sample code using the PaddleRS training model is curated in this directory. The code provides automatic downloading of sample data, and uses GPU to train the model.
 
-|Sample code path | Task | Model |
+|Sample Code Path | Task | Model |
 |------|--------|---------|
 |change_detection/bit.py | Change Detection | BIT |
 |change_detection/cdnet.py | Change Detection | CDNet |
@@ -36,75 +38,6 @@ Sample code using the PaddleRS training model is curated in this directory. The
 |semantic_segmentation/hrnet.py | Image Segmentation | HRNet |
 |semantic_segmentation/unet.py | Image Segmentation | UNet |
 
-## Environmental Preparation
-
-+ [PaddlePaddle installation](https://www.paddlepaddle.org.cn/install/quick)
-  - Version requirements: PaddlePaddle>=2.2.0
-
-+ PaddleRS installation
-
-The PaddleRS code will be updated as the development progresses. You can install the develop branch to use the latest features as follows:
-
-```shell
-git clone https://github.com/PaddlePaddle/PaddleRS
-cd PaddleRS
-git checkout develop
-pip install -r requirements.txt
-python setup.py install
-```
-
-If the downloading of dependencies is slow or times out when using `python setup.py install`, you can create `setup.cfg` in the same directory as `setup.py` and with the following content, then the download can be accelerated through Tsinghua source:
-
-```
-[easy_install]
-index-url=https://pypi.tuna.tsinghua.edu.cn/simple
-```
-
-+ (Optional) GDAL installation
-
-PaddleRS supports reading of various types of satellite data. To use the full data reading functionality of PaddleRS, you need to install GDAL as follows:
-
-  - Linux / MacOS
-
-conda is recommended for installation:
-
-```shell
-conda install gdal
-```
-
-  - Windows
-
-Windows users can download GDAL wheels from [this site](https://www.lfd.uci.edu/~gohlke/pythonlibs/#gdal). Please choose the wheel according to the Python version and the platform. Take *GDAL‑3.3.3‑cp39‑cp39‑win_amd64.whl* as an example, run the following command to install:
-
-```shell
-pip install GDAL‑3.3.3‑cp39‑cp39‑win_amd64.whl
-```
-
-### *Docker Installation
-
-1. Pull from dockerhub:
-
-```shell
-docker pull paddlepaddle/paddlers:1.0.0
-```
-
-- (Optional) Build from scratch. Select the base image for PaddlePaddle by setting `PPTAG`. You can build the image in a CPU-only environment or in GPU environments.
-
-```shell
-git clone https://github.com/PaddlePaddle/PaddleRS
-cd PaddleRS
-docker build -t <imageName> .  # default is 2.4.1-cpu version
-# docker build -t <imageName> . --build-arg PPTAG=2.4.1-gpu-cuda10.2-cudnn7.6-trt7.0  # One of the gpu versions of 2.4.1
-# Other Tag refer to: https://hub.docker.com/r/paddlepaddle/paddle/tags
-```
-
-2. Start a container
-
-```shell
-docker images  # View the ID of an image
-docker run -it <imageID>
-```
-
 ## Start Training
 
 + After PaddleRS is installed, run the following commands to launch training with a single GPU. The script will automatically download the training data. Take DeepLab V3+ image segmentation model as an example:
@@ -121,7 +54,7 @@ python tutorials/train/semantic_segmentation/deeplabv3p.py
 python -m paddle.distributed.launch --gpus 0,1 tutorials/train/semantic_segmentation/deeplabv3p.py
 ```
 
-## VisualDL Visual Training Metrics
+## Visualize Training Metrics via VisualDL
 
 Set the `use_vdl` argument passed to the `train()` method to `True`, and then the training log will be automatically saved in VisualDL format in a subdirectory named `vdl_log` under the directory specified by `save_dir`(a user-specified path) during the model training process. You can run the following command to start the VisualDL service and view the indicators and metrics. We also take DeepLab V3+ as an example: