diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
index 7ef6469c9737ad819f85416e61db7f7e120c9c64..4b426bb1ba6217e256748d5d2eb22bd7d30a0691 100644
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -123,7 +123,7 @@ When reporting issues, refer to this format:
- Raise your idea as an *issue* on [GitHub](https://github.com/mindspore-ai/mindspore/issues) or [Gitee](https://gitee.com/mindspore/mindspore/issues)
- If it is a new feature that needs lots of design details, a design proposal should also be submitted.
- After reaching consensus in the issue discussions and design proposal reviews, complete the development on the forked repo and submit a PR.
-- None of PRs is not permitted until it receives **2+ LGTM** from approvers. Please NOTICE that approver is NOT allowed to add *LGTM* on his own PR.
+- None of PRs is permitted until it receives **2+ LGTM** from approvers. Please NOTICE that approver is NOT allowed to add *LGTM* on his own PR.
- After PR is sufficiently discussed, it will get merged, abandoned or rejected depending on the outcome of the discussion.
**PRs advisory:**
diff --git a/CONTRIBUTING_CN.md b/CONTRIBUTING_CN.md
new file mode 100644
index 0000000000000000000000000000000000000000..7180d4f03ca0633e79e4e05d7ea2eb36a91b757d
--- /dev/null
+++ b/CONTRIBUTING_CN.md
@@ -0,0 +1,133 @@
+# 鏄囨€濊础鐚寚鍗�
+
+<!-- TOC -->
+
+- [鏄囨€濊础鐚寚鍗梋(#鏄囨€濊础鐚寚鍗�)
+ - [璐＄尞鑰呰鍙崗璁甝(#璐＄尞鑰呰鍙崗璁�)
+ - [寮€濮媇(#寮€濮�)
+ - [璐＄尞娴佺▼](#璐＄尞娴佺▼)
+ - [浠ｇ爜椋庢牸](#浠ｇ爜椋庢牸)
+ - [Fork-Pull寮€鍙戞ā寮廬(#fork-pull寮€鍙戞ā寮�)
+ - [鎶ュ憡闂](#鎶ュ憡闂)
+ - [鎻愪氦PR](#鎻愪氦-pr)
+
+<!-- /TPC -->
+
+## 璐＄尞鑰呰鍙崗璁�
+
+鍦ㄤ綘绗竴娆℃彁浜や唬鐮佺粰鏄囨€濈ぞ鍖轰箣鍓嶏紝闇€瑕佺缃睠LA锛屽浜庝釜浣撹础鐚€咃紝璇︽儏璇峰弬鐓CLA鍦ㄧ嚎鏂囨。](https://www.mindspore.cn/icla)
+
+## 寮€濮�
+
+- 鍙互鍦╗github](https://github.com/mindspore-ai/mindspore)鎴栬€匸Gitee](https://gitee.com/mindspore/mindspore)浠撳簱涓婅繘琛孎ork銆�
+- 闃呰[README_CN.md](README_CN.md)鍜孾瀹夎鎸囧](https://www.mindspore.cn/install)鏉ヨ幏鍙栭」鐩俊鎭拰缂栬瘧鎸囦护
+
+## 璐＄尞娴佺▼
+
+### 浠ｇ爜椋庢牸
+
+涓轰簡鏄囨€濈殑鏄撲簬瀹℃牳銆佺淮鎶ゅ拰寮€鍙戯紝璇烽伒寰涓嬭鑼�
+
+- 浠ｇ爜瑙勮寖
+
+ 鍦ㄦ槆鎬濈ぞ鍖猴紝*Python*浠ｇ爜椋庢牸鍙互鍙傝€僛Python PEP 8 Coding Style](https://pep8.org/)锛�*C++* 浠ｇ爜瑙勮寖鍙互鍙傝€僛Google C++ Coding Guidelines](http://google.github.io/styleguide/cppguide.html)銆�
+ 鍙互浣跨敤[CppLint](https://github.com/cpplint/cpplint)锛孾CppCheck](http://cppcheck.sourceforge.net)锛孾CMakeLint](https://github.com/cmake-lint/cmake-lint), [CodeSpell](https://github.com/codespell-project/codespell), [Lizard](http://www.lizard.ws), [ShellCheck](https://github.com/koalaman/shellcheck) 鍜� [PyLint](https://pylint.org)锛岃繘琛屼唬鐮佹牸寮忔鏌ワ紝寤鸿灏嗚繖浜涙彃浠跺畨瑁呭湪浣犵殑IDE涓娿€�
+
+- 鍗曞厓娴嬭瘯
+
+ *Python*鍗曞厓娴嬭瘯椋庢牸寤鸿閲囩敤[pytest](http://www.pytest.org/en/latest/)锛�*C++* 鍗曞厓娴嬭瘯寤鸿閲囩敤[Googletest Primer](https://github.com/google/googletest/blob/master/docs/primer.md)銆傛祴璇曠敤渚嬬殑娴嬭瘯鐩殑搴旇鍦ㄥ懡鍚嶄笂浣撶幇
+
+- 閲嶆瀯
+
+ 鎴戜滑榧撳姳寮€鍙戣€呴噸鏋勬垜浠殑浠ｇ爜锛屾潵娑堥櫎[code smell](https://en.wikipedia.org/wiki/Code_smell)銆傛墍鏈夌殑浠ｇ爜閮藉繀椤荤粡杩囦唬鐮侀鏍兼楠屻€佹祴璇曟楠岋紝閲嶆瀯浠ｇ爜涔熶笉渚嬪銆俒Lizard](http://www.lizard.ws)闃堝€硷紝瀵逛簬nloc((lines of code without comments)鏄�100锛宑nc (cyclomatic complexity number)鏄�20锛屽鏋滀綘鏀跺埌涓€涓�*Lizard*璀﹀憡锛屼綘蹇呴』鍦ㄥ悎鍏ヤ粨搴撳墠閲嶆瀯浣犵殑浠ｇ爜銆�
+
+- 鏂囨。
+
+ 鎴戜滑浣跨敤*MarkdownLint*鏉ユ鏌arkdown鏂囨。鐨勬牸寮忋€傛槆鎬濈殑闂ㄧ鍦ㄥ熀浜庨粯璁ら厤缃殑鎯呭喌涓嬩慨鏀逛簡濡備笅鐨勮鍒欙細
+ - MD007锛堟棤搴忓垪琛ㄧ缉杩涳級锛�**indent**鍙傛暟璁剧疆涓�**4**锛屽嵆鎵€鏈夋棤搴忓垪琛ㄧ殑鍐呭閮芥槸缂╄繘鍥涗釜瀛楄妭銆�
+ - MD009锛堣鏈┖鏍硷級锛�**br_spaces**鍙傛暟璁句负**2**锛屽嵆琛屾湯鍙互鏈�0涓垨鑰呬袱涓┖鏍笺€�
+ - MD029锛堟湁搴忓垪琛ㄥ簭鍙凤級锛�**style**鍙傛暟璁剧疆涓�**ordered**锛屽嵆鏈夊簭鍒楄〃鎸夌収鍗囧簭鎺掑垪
+
+ 鍏蜂綋缁嗚妭锛岃鍙傝€僛RULES](https://github.com/markdownlint/markdownlint/blob/master/docs/RULES.md)銆�
+
+### Fork-Pull寮€鍙戞ā寮�
+
+- Fork鏄囨€濅粨搴�
+
+ 鍦ㄦ彁浜ゆ槆鎬濋」鐩唬鐮佷箣鍓嶏紝璇风‘淇濇槆鎬濆凡缁忚fork鍒颁綘鑷繁鐨勪粨搴撳綋涓紝杩欏彲浠ヤ娇寰楁槆鎬濅粨搴撳拰浣犵殑浠撳簱骞惰寮€鍙戯紝鍥犳璇风‘淇濅袱鑰呬箣闂寸殑涓€鑷存€с€�
+
+- Clone杩滅▼浠撳簱
+
+ 濡傛灉浣犳兂涓嬭浇浠ｇ爜鍒颁綘鐨勬湰鍦版満鍣紝璇蜂娇鐢╣it銆�
+
+ ```shell
+ # For GitHub
+ git clone https://github.com/{insert_your_forked_repo}/mindspore.git
+ git remote add upstream https://github.com/mindspore-ai/mindspore.git
+ # For Gitee
+ git clone https://gitee.com/{insert_your_forked_repo}/mindspore.git
+ git remote add upstream https://gitee.com/mindspore/mindspore.git
+ ```
+
+- 鏈湴浠ｇ爜寮€鍙�
+
+ 涓轰簡淇濊瘉骞惰鍒嗘敮涔嬮棿鐨勪竴鑷存€э紝鍦ㄥ紑鍙戜唬鐮佸墠璇峰垱寤轰竴涓柊鐨勫垎鏀細
+
+ ```shell
+ git checkout -b {new_branch_name} origin/master
+ ```
+
+ 璇存槑锛歰rigin 涓烘槆鎬濆畼鏂逛粨搴擄紝娉ㄦ剰鍦ㄥ垱寤鸿嚜宸变粨搴撴椂灏介噺閬垮厤鍑虹幇origin鍏抽敭瀛楋紝浠ュ厤鍑虹幇娣锋穯
+
+- 鎺ㄩ€佷唬鐮佸埌杩滅▼浠撳簱
+
+ 鍦ㄦ洿鏂颁唬鐮佷箣鍚庯紝浣犻渶瑕佹寜鐓у涓嬫柟寮忔潵鎺ㄩ€佷唬鐮佸埌杩滅▼浠撳簱锛�
+
+ ```shell
+ git add .
+ git status # Check the update status
+ git commit -m "Your commit title"
+ git commit -s --amend #Add the concrete description of your commit
+ git push origin {new_branch_name}
+ ```
+
+- 瀵规槆鎬濅粨搴撴彁浜ゆ帹閫佽姹�--鎻愪氦PR
+
+ 鍦ㄦ渶鍚庝竴姝ワ紝浣犻渶瑕佸湪浣犵殑鏂板垎鏀拰鏄囨€漙master`鍒嗘敮鎻愪氦涓€涓瘮杈冭姹傘€傚湪杩欎箣鍚庯紝Jenkins闂ㄧ浼氳嚜鍔ㄨ繍琛屽垱寤烘祴璇曪紝涔嬪悗浣犵殑浠ｇ爜浼氳鍚堝叆鍒拌繙绋嬩富浠撳垎鏀笂銆�
+
+### 鎶ュ憡闂
+
+褰撲綘閬囧埌涓€涓棶棰樻椂,鎻愪氦涓€涓缁嗙殑闂鍗曚細瀵规槆鎬濇湁寰堝ぇ鐨勮础鐚紝鎴戜滑姘歌繙娆㈣繋濉啓璇︾粏銆佸叏闈㈢殑issue銆�
+
+褰撴姤鍛奿ssue鏃讹紝鍙傝€冧笅闈㈢殑鏍煎紡锛�
+
+- 浣犱娇鐢ㄧ殑鐜(mindspore銆乷s銆乸ython绛�)鏄粈涔堢増鏈殑
+- 杩欐槸涓€涓狟UG REPORT杩樻槸涓€涓狥EATURE REQUEST
+- 杩欎釜闂鐨勭被鍨嬫槸浠€涔堬紝鍦╥ssue dashbord涓婃坊鍔犳爣绛惧苟杩涜楂樹寒
+- 鍙戠敓浜嗕粈涔堥棶棰�
+- 浣犳湡鏈涚殑缁撴灉鏄粈涔�
+- 濡備綍澶嶇幇
+- 瀵瑰鏍镐汉鍛樺繀瑕佺殑娉ㄩ噴
+
+**issues 璀﹀憡:**
+
+**濡備綍纭畾鍝竴涓猧ssue鏄綘瑕佽В鍐崇殑锛�** 璇锋坊鍔犱竴浜沜ommits鍦ㄨ繖涓猧ssue涓婏紝浠ユ鏉ュ憡璇夊叾浠栦汉浣犲皢浼氬鐞嗗畠銆�
+**濡傛灉涓€涓猧ssue宸茬粡琚墦寮€涓€娈垫椂闂翠簡锛�** 寤鸿鍦ㄥ姩鎵嬭В鍐宠繖涓猧ssue涔嬪墠鍏堟鏌ヤ竴涓嬫槸鍚﹁繕瀛樺湪銆�
+**濡傛灉浣犺В鍐充簡涓€涓綘鑷繁鎻愮殑issue锛�** 鍦ㄥ叧闂箣鍓嶉渶瑕佽鍏朵粬浜虹煡閬撱€�
+**濡傛灉浣犲笇鏈涜繖涓猧ssue灏藉揩琚В鍐筹紝** 璇风粰瀹冩墦涓婃爣绛撅紝浣犲彲浠ュ湪[label list](https://gitee.com/mindspore/community/blob/master/sigs/dx/docs/labels.md)鎵惧埌涓嶅悓鐨勬爣绛俱€�
+
+鍏蜂綋鍙互鍙傜収璇閾炬帴](https://gitee.com/mindspore/models/issues)涓嬪凡缁忔彁浜ょ殑issue绀轰緥
+
+### 鎻愪氦PR
+
+- 鍦� [GitHub](https://github.com/mindspore-ai/mindspore/issues) 鎴栬€� [Gitee](https://gitee.com/mindspore/mindspore/issues) 閽堝涓€涓�*issue*鎻愬嚭浣犵殑瑙ｅ喅鏂规銆�
+- 鍦ㄨ棰樿璁哄拰璁捐鏂规瀹℃牳杈炬垚鍏辫瘑鍚庯紝fork鍚庡畬鎴愬紑鍙戝悗鎻愪氦PR
+- 璐＄尞鑰呯殑浠ｇ爜闇€瑕佽嚦灏戜袱涓猚ommitter*LGTM*锛孭R鎵嶅彲浠ヨ鍏佽鎺ㄩ€侊紝娉ㄦ剰璐＄尞鑰呬笉鍏佽鍦ㄨ嚜宸辩殑PR涓婃坊鍔�*LGTM*銆�
+- 鍦≒R琚缁嗚瘎瀹″悗锛岃繖涓狿R灏嗕細琚‘瀹氳兘鍚﹁鍚堝叆銆�
+
+**PRs 璀﹀憡:**
+
+- 搴旈伩鍏嶄换浣曟棤鍏崇殑鏇存敼
+- 纭繚鎮ㄧ殑鎻愪氦鍘嗗彶璁板綍鍙湁涓€娆★紝鍦ㄧ‘瀹氭槸鏈€缁堢増鎻愪氦璁板綍鍚庯紝灏嗕互寰€鎻愪氦璁板綍鍚堝苟銆�
+- 濮嬬粓淇濇寔浣犵殑鍒嗘敮涓庝富鍒嗘敮涓€鑷淬€�
+- 瀵逛簬淇bug鐨凱R锛岃纭繚閾炬帴涓婁簡issue
diff --git a/how_to_contribute/CONTRIBUTING_ATTENTION.md b/how_to_contribute/CONTRIBUTING_ATTENTION.md
new file mode 100644
index 0000000000000000000000000000000000000000..bb2c802ed37d68dfdce69528ccfe40cd4b89a542
--- /dev/null
+++ b/how_to_contribute/CONTRIBUTING_ATTENTION.md
@@ -0,0 +1,139 @@
+# How To Contribute MindSpore ModelZoo
+
+<!-- TOC -->
+
+- [How To Contribute MindSpore ModelZoo](#how-to-contribute-mindSpore-modelZoo)
+ - [Preparation](#preparation)
+ - [Understand Contribution Agreements And Procedures](#understand-contribution-agreements-and-procedures)
+ - [Define Goals For Your Contributions](#define-goals-for-your-contributions)
+ - [Submit Code](#submit-code)
+ - [CodeStyle](#codestyle)
+ - [Directory Structure](#directory-structure)
+ - [ReadMe](#readme)
+ - [Third Party Reference](#third-party-reference)
+ - [Reference Additional Python Libraries](#reference-additional-python-libraries)
+ - [Reference Third-Party Open Source Code](#reference-third-party-open-source-code)
+ - [Reference Other System Libraries](#reference-other-system-libraries)
+ - [Submit The Self-Check List](#submit-the-self-check-list)
+ - [Maintenance And Communication](#maintenance-and-communication)
+
+<!-- TOC -->
+
+This guidance is used to clarify the ModelZoo contribution specification to ensure that many developers can participate in the construction of ModelZoo in a relatively uniform style and process.
+
+## Preparation
+
+### Understand Contribution Agreements And Procedures
+
+You should first consult MindSpore's [CONTRIBUTING.md](../CONTRIBUTING.md) instructions to understand the Open source agreement and how MindSpore works, and make sure you have signed the CLA.
+
+<!--
+### Define Goals For Your Contributions
+
+If you want to contribute, we recommend that you start with some of the easier issues. You can find some simple bugfix jobs in the following list.
+
+- [wanted bugfix](https://gitee.com/mindspore/mindspore/issues?assignee_id=&author_id=&branch=&issue_search=&label_ids=58021213&label_text=kind/bug&milestone_id=&program_id=&scope=&sort=newest&state=open)
+
+If you can make independent network contributions, you can find our list of networks to implement in the list below.
+
+- [wanted implement](https://gitee.com/mindspore/mindspore/issues?assignee_id=&author_id=&branch=&issue_search=&label_ids=58022151&label_text=device%2Fascend&milestone_id=&program_id=&scope=&sort=newest&state=open)
+
+Remember to send a reply after the issue is selected to let others know that you are working on the issue. When you're done with something, also go back to Issue to update your work. If you have problems with the process, feel free to update your progress in the issue.
+-->
+
+## Submit Code
+
+### CodeStyle
+
+Reference [CONTRIBUTING.md](../CONTRIBUTING.md), you should make sure your code is consistent with MindSpore's existing CodeStyle.
+
+### Directory Structure
+
+```shell
+model_zoo
+鈹溾攢鈹€ official # Officially supported models
+鈹� 鈹斺攢鈹€ XXX # Model name
+鈹� 鈹溾攢鈹€ README.md # Model specification document
+鈹� 鈹溾攢鈹€ requirements.txt # Dependency documentation
+鈹� 鈹溾攢鈹€ eval.py # Accuracy verification script
+鈹� 鈹溾攢鈹€ export.py # Inference model export script
+鈹� 鈹溾攢鈹€ scripts # script file
+鈹� 鈹偮犅� 鈹溾攢鈹€ run_distributed_train.sh # Distributed training script
+鈹� 鈹偮犅� 鈹溾攢鈹€ run_eval.sh # Verify the script
+鈹� 鈹偮犅� 鈹斺攢鈹€ run_standalone_train.sh # Single machine training script
+鈹� 鈹溾攢鈹€ src # Model definition source directory
+鈹� 鈹偮犅� 鈹溾攢鈹€ XXXNet.py # Definition of model structure
+鈹� 鈹偮犅� 鈹溾攢鈹€ callback.py # Callback function definition
+鈹� 鈹偮犅� 鈹溾攢鈹€ config.py # Model configuration parameter file
+鈹� 鈹偮犅� 鈹斺攢鈹€ dataset.py # Data set processing definition
+鈹� 鈹溾攢鈹€ ascend_infer # (Optional) Scripts for offline reasoning on Ascend reasoning devices
+鈹� 鈹溾攢鈹€ third_party # (Optional) Third-party code
+鈹� 鈹偮犅� 鈹斺攢鈹€ XXXrepo # (Optional) Complete code cloned from a third-party repository
+鈹� 鈹斺攢鈹€ train.py # Training script
+鈹溾攢鈹€ research # Unofficial research script
+鈹溾攢鈹€ community # Partner script links
+鈹斺攢鈹€ utils # General tool for modeling
+```
+
+You can follow these guidelines and make changes to the template to suit your own implementation
+
+1. Only executable scripts with the 'main method' are placed in the root directory of the model. The definition files of the model are placed in the 'src' directory, which can organize the hierarchy according to the complexity of the model.
+
+2. The configuration parameters should be separated from the network definition, and all configurable parameters should be defined in the 'src/config.py' file.
+
+3. Upload content should contain only scripts, code, and documentation, and **do not upload** any data sets, as well as directories and files generated during the run.
+
+4. Third_party is used to store third-party code that needs to be referenced, but you should not copy the code directly to the directory and upload it. Instead, you should use the form of git link and download it when you use it.
+
+5. The code for each model should be its own closure that can be migrated and used independently and should not rely on code outside the model directory. Utils is a generic tool, not a generic library.
+
+6. **Do not include** any of your personal information, such as your host IP, personal password, local directory, etc.
+
+### ReadMe
+
+Each AI model needs a corresponding 'readme.md' documentation that describes the current model implementation and communicates the following information to other users:
+
+1. What model is this? What are the sources and references?
+2. What does the current implementation contain?
+3. How to use existing implementations?
+4. How does the model perform?
+
+For this, we provide a basic [README TEMPLATE](./README_TEMPLATE.md) that you should refer to to refine your documentation, as well as README for other existing models.
+
+### Third Party Reference
+
+#### Reference Additional Python Libraries
+
+Be sure to specify any additional Python libraries you need and corresponding versions (if explicitly required) in the 'requirements.txt' file. You should prioritize third-party libraries that are compatible with the MindSpore framework.
+
+#### Reference Third-Party Open Source Code
+
+You should make sure that the code you submit is your own original development.
+
+When you need to leverage the power of the open source community, you should first use mature and trusted open source projects and verify that the open source license of your chosen open source project meets the requirements.
+
+When you use open source code, the correct way to use it is to get the code from your Git address and archive it in a separate 'third_party' directory to keep it isolated from your own code. **Do not copy the corresponding code snippets into your own submission.**
+
+#### Reference Other System Libraries
+
+You should reduce your reliance on unique system libraries, as this often means that your commit is hard to reuse across different systems.
+
+When you do need to use some unique system dependencies to get things done, you need to specify how to get and install them in the instructions.
+
+### Submit The Self-Check List
+
+Your submitted code should be fully reviewed and self-checked by referring to the following checklist
+
+- [ ] Code style conforms to specification
+- [ ] Code adds comments where necessary
+- [ ] The document has been synchronized
+- [ ] Synchronously adds the necessary test cases
+- [ ] All third party dependencies are explained, including code references, Python libraries, data sets, pre-trained models, etc
+- [ ] The project organization complies with the requirements in [Directory Structure](#directory-structure).
+- [ ] Complete readme writing and pass CI tests
+
+## Maintenance And Communication
+
+We appreciate your contribution to the MindSpore community, and we encourage you to keep an eye on your code after you complete a submission. You can mark your signature, email address and other contact information in the README of the submitted model, and keep an eye on your Gitee and Github information.
+
+Other developers may be using the model you submitted and may have some questions during use. In this case, you can communicate with you in detail through issues, in-site messages, emails, etc.
diff --git a/how_to_contribute/CONTRIBUTING.md b/how_to_contribute/CONTRIBUTING_ATTENTION_CN.md
similarity index 68%
rename from how_to_contribute/CONTRIBUTING.md
rename to how_to_contribute/CONTRIBUTING_ATTENTION_CN.md
index 3e8b4ef3e4f2eb3062b3feb017391484c6578f54..641dca82dbf5b467ceea81cd148e3d011f864858 100644
--- a/how_to_contribute/CONTRIBUTING.md
+++ b/how_to_contribute/CONTRIBUTING_ATTENTION_CN.md
@@ -25,7 +25,7 @@
### 浜嗚В璐＄尞鍗忚涓庢祦绋�
-浣犲簲璇ヤ紭鍏堝弬鑰僊indSpore鐨刐CONTRIBUTE.md](../CONTRIBUTING.md)璇存槑鏉ョ悊瑙indSpore鐨勫紑婧愬崗璁拰杩愪綔鏂瑰紡锛屽苟纭繚鑷繁宸插畬鎴怌LA鐨勭缃层€�
+浣犲簲璇ヤ紭鍏堝弬鑰僊indSpore鐨刐CONTRIBUTING_CN.md](../CONTRIBUTING_CN.md)璇存槑鏉ョ悊瑙indSpore鐨勫紑婧愬崗璁拰杩愪綔鏂瑰紡锛屽苟纭繚鑷繁宸插畬鎴怌LA鐨勭缃层€�
<!--
### 纭畾鑷繁璐＄尞鐨勭洰鏍�
@@ -45,7 +45,7 @@
### CodeStyle
-鍙傝€僛CONTRIBUTE.md](../CONTRIBUTING.md)涓叧浜嶤odeStyle鐨勮鏄庯紝浣犲簲璇ョ‘淇濊嚜宸辩殑浠ｇ爜涓嶮indSpore鐨勭幇鏈変唬鐮侀鏍间繚鎸佷竴鑷淬€�
+鍙傝€僛CONTRIBUTING_CN.md](../CONTRIBUTING_CN.md)涓叧浜嶤odeStyle鐨勮鏄庯紝浣犲簲璇ョ‘淇濊嚜宸辩殑浠ｇ爜涓嶮indSpore鐨勭幇鏈変唬鐮侀鏍间繚鎸佷竴鑷淬€�
### 鐩綍缁撴瀯
@@ -53,35 +53,35 @@
```shell
model_zoo
-鈹溾攢鈹€ official # 瀹樻柟鏀寔妯″瀷
-鈹� 鈹斺攢鈹€ XXX # 妯″瀷鍚�
-鈹� 鈹溾攢鈹€ README.md # 妯″瀷璇存槑鏂囨。
-鈹� 鈹溾攢鈹€ requirements.txt # 渚濊禆璇存槑鏂囦欢
-鈹� 鈹溾攢鈹€ eval.py # 绮惧害楠岃瘉鑴氭湰
-鈹� 鈹溾攢鈹€ export.py # 鎺ㄧ悊妯″瀷瀵煎嚭鑴氭湰
-鈹� 鈹溾攢鈹€ scripts # 鑴氭湰鏂囦欢
-鈹� 鈹偮犅� 鈹溾攢鈹€ run_distributed_train.sh # 鍒嗗竷寮忚缁冭剼鏈�
-鈹� 鈹偮犅� 鈹溾攢鈹€ run_eval.sh # 楠岃瘉鑴氭湰
-鈹� 鈹偮犅� 鈹斺攢鈹€ run_standalone_train.sh # 鍗曟満璁粌鑴氭湰
-鈹� 鈹溾攢鈹€ src # 妯″瀷瀹氫箟婧愮爜鐩綍
-鈹� 鈹偮犅� 鈹溾攢鈹€ XXXNet.py # 妯″瀷缁撴瀯瀹氫箟
-鈹� 鈹偮犅� 鈹溾攢鈹€ callback.py # 鍥炶皟鍑芥暟瀹氫箟
-鈹� 鈹偮犅� 鈹溾攢鈹€ config.py # 妯″瀷閰嶇疆鍙傛暟鏂囦欢
-鈹� 鈹偮犅� 鈹斺攢鈹€ dataset.py # 鏁版嵁闆嗗鐞嗗畾涔�
-鈹� 鈹溾攢鈹€ ascend_infer # 锛堝彲閫夛級鐢ㄤ簬鍦ˋscend鎺ㄧ悊璁惧涓婅繘琛岀绾挎帹鐞嗙殑鑴氭湰
-鈹� 鈹溾攢鈹€ third_party # 锛堝彲閫夛級绗笁鏂逛唬鐮�
-鈹� 鈹偮犅� 鈹斺攢鈹€ XXXrepo # 锛堝彲閫夛級瀹屾暣鍏嬮殕鑷涓夋柟浠撳簱鐨勪唬鐮�
-鈹� 鈹斺攢鈹€ train.py # 璁粌鑴氭湰
-鈹溾攢鈹€ research # 闈炲畼鏂圭爺绌惰剼鏈�
-鈹溾攢鈹€ community # 鍚堜綔鏂硅剼鏈摼鎺�
-鈹斺攢鈹€ utils # 妯″瀷閫氱敤宸ュ叿
+鈹溾攢鈹€ official # 瀹樻柟鏀寔妯″瀷
+鈹� 鈹斺攢鈹€ XXX # 妯″瀷鍚�
+鈹� 鈹溾攢鈹€ README.md # 妯″瀷璇存槑鏂囨。
+鈹� 鈹溾攢鈹€ requirements.txt # 渚濊禆璇存槑鏂囦欢
+鈹� 鈹溾攢鈹€ eval.py # 绮惧害楠岃瘉鑴氭湰
+鈹� 鈹溾攢鈹€ export.py # 鎺ㄧ悊妯″瀷瀵煎嚭鑴氭湰
+鈹� 鈹溾攢鈹€ scripts # 鑴氭湰鏂囦欢
+鈹� 鈹偮犅� 鈹溾攢鈹€ run_distributed_train.sh # 鍒嗗竷寮忚缁冭剼鏈�
+鈹� 鈹偮犅� 鈹溾攢鈹€ run_eval.sh # 楠岃瘉鑴氭湰
+鈹� 鈹偮犅� 鈹斺攢鈹€ run_standalone_train.sh # 鍗曟満璁粌鑴氭湰
+鈹� 鈹溾攢鈹€ src # 妯″瀷瀹氫箟婧愮爜鐩綍
+鈹� 鈹偮犅� 鈹溾攢鈹€ XXXNet.py # 妯″瀷缁撴瀯瀹氫箟
+鈹� 鈹偮犅� 鈹溾攢鈹€ callback.py # 鍥炶皟鍑芥暟瀹氫箟
+鈹� 鈹偮犅� 鈹溾攢鈹€ config.py # 妯″瀷閰嶇疆鍙傛暟鏂囦欢
+鈹� 鈹偮犅� 鈹斺攢鈹€ dataset.py # 鏁版嵁闆嗗鐞嗗畾涔�
+鈹� 鈹溾攢鈹€ ascend_infer # 锛堝彲閫夛級鐢ㄤ簬鍦ˋscend鎺ㄧ悊璁惧涓婅繘琛岀绾挎帹鐞嗙殑鑴氭湰
+鈹� 鈹溾攢鈹€ third_party # 锛堝彲閫夛級绗笁鏂逛唬鐮�
+鈹� 鈹偮犅� 鈹斺攢鈹€ XXXrepo # 锛堝彲閫夛級瀹屾暣鍏嬮殕鑷涓夋柟浠撳簱鐨勪唬鐮�
+鈹� 鈹斺攢鈹€ train.py # 璁粌鑴氭湰
+鈹溾攢鈹€ research # 闈炲畼鏂圭爺绌惰剼鏈�
+鈹溾攢鈹€ community # 鍚堜綔鏂硅剼鏈摼鎺�
+鈹斺攢鈹€ utils # 妯″瀷閫氱敤宸ュ叿
```
浣犲彲浠ュ弬鐓т互涓嬪師鍒欙紝鏍规嵁鑷繁鐨勯渶瑕佸湪妯℃澘鍩虹涓婂仛涓€浜涢€傞厤鑷繁瀹炵幇鐨勪慨鏀�
1. 妯″瀷鏍圭洰褰曚笅鍙斁缃甫鏈塦main鏂规硶`鐨勫彲鎵ц鑴氭湰锛屾ā鍨嬬殑瀹氫箟鏂囦欢缁熶竴鏀惧湪`src`鐩綍涓嬶紝璇ョ洰褰曚笅鍙互鏍规嵁鑷繁妯″瀷鐨勫鏉傜▼搴﹁嚜琛岀粍缁囧眰娆＄粨鏋勩€�
-2. 閰嶇疆鍙傛暟搴斿綋涓庣綉缁滃畾涔夊垎绂伙紝灏嗘墍鏈夊彲閰嶇疆鐨勫弬鏁版娊绂诲埌`src/config.py`鏂囦欢涓粺涓€瀹氫箟銆�
-3. 涓婁紶鍐呭搴斿綋鍙寘鍚剼鏈€佷唬鐮佸拰鏂囨。锛�**涓嶈涓婁紶**浠讳綍鏁版嵁闆嗘垨checkpoint涔嬬被鐨勬暟鎹枃浠躲€�
+2. 閰嶇疆鍙傛暟搴斿綋涓庣綉缁滃畾涔夊垎绂伙紝灏嗘墍鏈夊彲閰嶇疆鐨勫弬鏁版娊绂诲埌`config/`鏂囦欢澶逛腑锛屼娇鐢�.yml鏍煎紡鏂囦欢缁熶竴瀹氫箟銆�
+3. 涓婁紶鍐呭搴斿綋鍙寘鍚剼鏈€佷唬鐮佸拰鏂囨。锛�**涓嶈涓婁紶**浠讳綍鏁版嵁闆嗐€佷互鍙婅繍琛岃繃绋嬩腑鎵€浜х敓鐨勭洰褰曞拰鏂囦欢銆�
4. third_party鐢ㄤ簬瀛樻斁闇€瑕佸紩鐢ㄧ殑绗笁鏂逛唬鐮侊紝浣嗘槸涓嶈鐩存帴灏嗕唬鐮佹嫹璐濆埌鐩綍涓嬩笂浼狅紝鑰屽簲璇ヤ娇鐢╣it閾炬帴鐨勫舰寮忥紝鍦ㄤ娇鐢ㄦ椂涓嬭浇銆�
5. 姣忎釜妯″瀷鐨勪唬鐮佸簲褰撹嚜鎴愰棴鍖咃紝鍙互鐙珛鐨勮縼绉讳娇鐢紝涓嶅簲褰撲緷璧栨ā鍨嬬洰褰曚互澶栫殑鍏朵粬浠ｇ爜銆倁tils鍐呭彧鏄€氱敤宸ュ叿锛屽苟闈為€氱敤鍑芥暟搴撱€�
6. 涓婁紶鍐呭涓�**涓嶈鍖呭惈**浠讳綍浣犵殑涓汉淇℃伅锛屼緥濡備綘鐨勪富鏈篒P锛屼釜浜哄瘑鐮侊紝鏈湴鐩綍绛夈€�
@@ -95,7 +95,7 @@ model_zoo
3. 濡備綍浣跨敤鐜版湁鐨勫疄鐜帮紵
4. 杩欎釜妯″瀷琛ㄧ幇濡備綍锛�
-瀵规锛屾垜浠彁渚涗簡涓€涓熀纭€鐨刐README妯＄増](./README_template.md)锛屼綘搴旇鍙傝€冩妯＄増鏉ュ畬鍠勮嚜宸辩殑璇存槑鏂囨。, 涔熷彲浠ュ弬鑰冨叾浠栫幇鏈夋ā鍨嬬殑readme銆�
+瀵规锛屾垜浠彁渚涗簡涓€涓熀纭€鐨刐README妯＄増](./README_TEMPLATE_CN.md)锛屼綘搴旇鍙傝€冩妯＄増鏉ュ畬鍠勮嚜宸辩殑璇存槑鏂囨。, 涔熷彲浠ュ弬鑰冨叾浠栫幇鏈夋ā鍨嬬殑readme銆�
### 鍏充簬绗笁鏂瑰紩鐢�
@@ -127,6 +127,7 @@ model_zoo
- [ ] 鍚屾娣诲姞浜嗗繀瑕佺殑娴嬭瘯鐢ㄤ緥
- [ ] 鎵€鏈夌涓夋柟渚濊禆閮藉凡缁忚鏄庯紝鍖呮嫭浠ｇ爜寮曠敤锛宲ython搴擄紝鏁版嵁闆嗭紝棰勮缁冩ā鍨嬬瓑
- [ ] 宸ョ▼缁勭粐缁撴瀯绗﹀悎[鐩綍缁撴瀯](#鐩綍缁撴瀯)涓殑瑕佹眰銆�
+- [ ] 瀹屾垚readme缂栧啓锛岄€氳繃CI娴嬭瘯
## 缁存姢涓庝氦娴�
diff --git a/how_to_contribute/README_TEMPLATE.md b/how_to_contribute/README_TEMPLATE.md
new file mode 100644
index 0000000000000000000000000000000000000000..95b05afd13c2ce23cee3e3d8a08deaa8b4f18db8
--- /dev/null
+++ b/how_to_contribute/README_TEMPLATE.md
@@ -0,0 +1,147 @@
+<TOC>
+
+# Title, Model name
+
+> The Description of Model. The paper present this model.
+
+## Model Architecture
+
+> There could be various architecture about some model. Represent the architecture of your implementation.
+
+## Features(optional)
+
+> Represent the distinctive feature you used in the model implementation. Such as distributed auto-parallel or some special training trick.
+
+## Dataset
+
+> Provide the information of the dataset you used. Check the copyrights of the dataset you used, usually you need to provide the hyperlink to download the dataset.
+
+## Requirements
+
+> Provide details of the software required, including:
+>
+> * The additional python package required. Add a `requirements.txt` file to the root dir of model for installing dependencies.
+> * The necessary third-party code.
+> * Some other system dependencies.
+> * Some additional operations before training or prediction.
+
+## Quick Start
+
+> How to take a try without understanding anything about the model.
+
+## Script Description
+
+> The section provide the detail of implementation.
+
+### Scripts and Sample Code
+
+> Explain every file in your project.
+
+### Script Parameter
+
+> Explain every parameter of the model. Especially the parameters in `config.py`.
+
+## Training
+
+> Provide training information.
+
+### Training Process
+
+> Provide the usage of training scripts.
+
+e.g. Run the following command for distributed training on Ascend.
+
+```shell
+bash run_distribute_train.sh [RANK_TABLE_FILE] [PRETRAINED_MODEL]
+```
+
+### Transfer Training(Optional)
+
+> Provide the guidelines about how to run transfer training based on an pretrained model.
+
+### Training Result
+
+> Provide the result of training.
+
+e.g. Training checkpoint will be stored in `XXXX/ckpt_0`. You will get result from log file like the following:
+
+```
+epoch: 11 step: 7393 ,rpn_loss: 0.02003, rcnn_loss: 0.52051, rpn_cls_loss: 0.01761, rpn_reg_loss: 0.00241, rcnn_cls_loss: 0.16028, rcnn_reg_loss: 0.08411, rcnn_mask_loss: 0.27588, total_loss: 0.54054
+epoch: 12 step: 7393 ,rpn_loss: 0.00547, rcnn_loss: 0.39258, rpn_cls_loss: 0.00285, rpn_reg_loss: 0.00262, rcnn_cls_loss: 0.08002, rcnn_reg_loss: 0.04990, rcnn_mask_loss: 0.26245, total_loss: 0.39804
+```
+
+## Evaluation
+
+### Evaluation Process
+
+> Provide the use of evaluation scripts.
+
+### Evaluation Result
+
+> Provide the result of evaluation.
+
+## Performance
+
+### Training Performance
+
+> Provide the detail of training performance including finishing loss, throughput, checkpoint size and so on.
+
+e.g. you can reference the following template
+
+| Parameters | Ascend 910 | GPU |
+| -------------------------- | ------------------------------------------------------------ | ----------------------------------------------|
+| Model Version | ResNet18 | ResNet18 |
+| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 | PCIE V100-32G |
+| uploaded Date | 02/25/2021 (month/day/year) | 07/23/2021 (month/day/year) |
+| MindSpore Version | 1.1.1 | 1.3.0 |
+| Dataset | CIFAR-10 | CIFAR-10 |
+| Training Parameters | epoch=90, steps per epoch=195, batch_size = 32 | epoch=90, steps per epoch=195, batch_size = 32|
+| Optimizer | Momentum | Momentum |
+| Loss Function | Softmax Cross Entropy | Softmax Cross Entropy |
+| outputs | probability | probability |
+| Loss | 0.0002519517 | 0.0015517382 |
+| Speed | 13 ms/step锛�8pcs锛� | 29 ms/step锛�8pcs锛� |
+| Total time | 4 mins | 11 minds |
+| Parameters (M) | 11.2 | 11.2 |
+| Checkpoint for Fine tuning | 86M (.ckpt file) | 85.4 (.ckpt file) |
+| Scripts | [link](https://gitee.com/mindspore/models/tree/master/official/cv/resnet) |
+
+### Inference Performance
+
+> Provide the detail of evaluation performance including latency, accuracy and so on.
+
+e.g. you can reference the following template
+
+| Parameters | Ascend |
+| ------------------- | --------------------------- |
+| Model Version | ResNet18 |
+| Resource | Ascend 910; OS Euler2.8 |
+| Uploaded Date | 02/25/2021 (month/day/year) |
+| MindSpore Version | 1.1.1 |
+| Dataset | CIFAR-10 |
+| batch_size | 32 |
+| outputs | probability |
+| Accuracy | 94.02% |
+| Model for inference | 43M (.air file) |
+
+## Description of Random Situation
+
+> Explain the random situation in the project.
+
+## Reference Example
+
+[maskrcnn_readme](https://gitee.com/mindspore/models/blob/master/official/cv/maskrcnn/README.md)
+
+## Contributions
+
+If you want to contribute, please review the [contribution guidelines](https://gitee.com/mindspore/models/blob/master/CONTRIBUTING.md) and [how_to_contribute](https://gitee.com/mindspore/models/tree/master/how_to_contribute)
+
+### Contributors
+
+- Training and evaluation on Ascend910 is contributed by `XXX`.
+- Inference on Ascend310 is contributed by `XXX`.
+- ...
+
+## ModeZoo Homepage
+
+Please check the official [homepage](https://gitee.com/mindspore/models).
diff --git a/how_to_contribute/README_TEMPLATE_CN.md b/how_to_contribute/README_TEMPLATE_CN.md
new file mode 100644
index 0000000000000000000000000000000000000000..b4baf4aac09074f385a6377904e60e25793c8dfb
--- /dev/null
+++ b/how_to_contribute/README_TEMPLATE_CN.md
@@ -0,0 +1,143 @@
+<TOC>
+
+# 鏍囬锛� 妯″瀷鍚嶇О
+
+> 鍙互鏄ā鍨嬬殑涓嶅悓鏋舵瀯锛屽悕绉板彲浠ヤ唬琛ㄤ綘鎵€瀹炵幇鐨勬ā鍨嬫灦鏋�
+
+## 鐗规€э紙鍙€夛級
+
+> 灞曠ず浣犲湪妯″瀷瀹炵幇涓娇鐢ㄧ殑鐗规€э紝渚嬪鍒嗗竷寮忚嚜鍔ㄥ苟琛屾垨鑰呬竴浜涚壒娈婄殑璁粌鎶€宸�
+
+## 鏁版嵁闆�
+
+> 鎻愪緵浣犳墍浣跨敤鐨勬暟鎹俊鎭紝妫€鏌ユ暟鎹増鏉冿紝閫氬父鎯呭喌涓嬩綘闇€瑕佹彁渚涗笅杞芥暟鎹殑閾炬帴
+
+## 鐜瑕佹眰
+
+> 鎻愪緵杩愯璇ヤ唬鐮佸墠闇€瑕佺殑鐜閰嶇疆锛屽寘鎷細
+>
+> * python绗笁鏂瑰簱锛屽湪妯″瀷root鏂囦欢澶逛笅娣诲姞涓€涓�'requirements.txt'鏂囦欢锛屾枃浠跺唴璇存槑妯″瀷渚濊禆鐨勭涓夋柟搴�
+> * 蹇呰鐨勭涓夋柟浠ｇ爜
+> * 鍏朵粬鐨勭郴缁熶緷璧�
+> * 鍦ㄨ缁冩垨鎺ㄧ悊鍓嶉澶栫殑鎿嶄綔
+
+## 蹇€熷叆闂�
+
+> 浣跨敤涓€鏉′粈涔堟牱鐨勫懡浠ゅ彲浠ョ洿鎺ヨ繍琛�
+
+## 鑴氭湰璇存槑
+
+> 鎻愪緵瀹炵幇鐨勭粏鑺�
+
+### 鑴氭湰鍜屾牱渚嬩唬鐮�
+
+> 鎻忚堪椤圭洰涓瘡涓枃浠剁殑浣滅敤
+
+### 鑴氭湰鍙傛暟
+
+> 娉ㄩ噴妯″瀷涓殑姣忎釜鍙傛暟锛岀壒鍒槸`config.py`涓殑鍙傛暟
+
+## 璁粌杩囩▼
+
+> 鎻愪緵璁粌淇℃伅
+
+### 鐢ㄦ硶
+
+> 鎻愪緵璁粌鑴氭湰鐨勪娇鐢ㄦ儏鍐�
+
+渚嬪锛氬湪鏄囪吘涓婁娇鐢ㄥ垎甯冨紡璁粌杩愯涓嬮潰鐨勫懡浠�
+
+```shell
+bash run_distribute_train.sh [RANK_TABLE_FILE] [PRETRAINED_MODEL]
+```
+
+### 杩佺Щ璁粌锛堝彲閫夛級
+
+> 鎻愪緵濡備綍鏍规嵁棰勮缁冩ā鍨嬭繘琛岃縼绉昏缁冪殑鎸囧崡
+
+### 璁粌缁撴灉
+
+> 鎻愪緵璁粌缁撴灉
+
+渚嬪锛氳缁僣heckpoint灏嗚淇濆瓨鍦╜XXXX/ckpt_0`涓紝浣犲彲浠ヤ粠濡備笅鐨刲og鏂囦欢涓幏鍙栫粨鏋�
+
+```
+epoch: 11 step: 7393 ,rpn_loss: 0.02003, rcnn_loss: 0.52051, rpn_cls_loss: 0.01761, rpn_reg_loss: 0.00241, rcnn_cls_loss: 0.16028, rcnn_reg_loss: 0.08411, rcnn_mask_loss: 0.27588, total_loss: 0.54054
+epoch: 12 step: 7393 ,rpn_loss: 0.00547, rcnn_loss: 0.39258, rpn_cls_loss: 0.00285, rpn_reg_loss: 0.00262, rcnn_cls_loss: 0.08002, rcnn_reg_loss: 0.04990, rcnn_mask_loss: 0.26245, total_loss: 0.39804
+```
+
+## 鎺ㄧ悊
+
+### 鎺ㄧ悊杩囩▼
+
+> 鎻愪緵鎺ㄧ悊鑴氭湰
+
+### 鎺ㄧ悊缁撴灉
+
+> 鎻愪緵鎺ㄧ悊缁撴灉
+
+## 鎬ц兘
+
+### 璁粌鎬ц兘
+
+鎻愪緵鎮ㄨ缁冩€ц兘鐨勮缁嗘弿杩帮紝渚嬪finishing loss, throughput, checkpoint size绛�
+
+浣犲彲浠ュ弬鑰冨涓嬫ā鏉�
+
+| Parameters | Ascend 910 | GPU |
+| -------------------------- | ------------------------------------------------------------ | ----------------------------------------------|
+| Model Version | ResNet18 | ResNet18 |
+| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 | PCIE V100-32G |
+| uploaded Date | 02/25/2021 (month/day/year) | 07/23/2021 (month/day/year) |
+| MindSpore Version | 1.1.1 | 1.3.0 |
+| Dataset | CIFAR-10 | CIFAR-10 |
+| Training Parameters | epoch=90, steps per epoch=195, batch_size = 32 | epoch=90, steps per epoch=195, batch_size = 32|
+| Optimizer | Momentum | Momentum |
+| Loss Function | Softmax Cross Entropy | Softmax Cross Entropy |
+| outputs | probability | probability |
+| Loss | 0.0002519517 | 0.0015517382 |
+| Speed | 13 ms/step锛�8pcs锛� | 29 ms/step锛�8pcs锛� |
+| Total time | 4 mins | 11 minds |
+| Parameters (M) | 11.2 | 11.2 |
+| Checkpoint for Fine tuning | 86M (.ckpt file) | 85.4 (.ckpt file) |
+| Scripts | [link](https://gitee.com/mindspore/models/tree/master/official/cv/) |
+
+### 鎺ㄧ悊鎬ц兘
+
+> 鎻愪緵鎺ㄧ悊鎬ц兘鐨勮缁嗘弿杩帮紝鍖呮嫭鑰楁椂锛岀簿搴︾瓑
+
+浣犲彲浠ュ弬鐓у涓嬫ā鏉�
+
+| Parameters | Ascend |
+| ------------------- | --------------------------- |
+| Model Version | ResNet18 |
+| Resource | Ascend 910; OS Euler2.8 |
+| Uploaded Date | 02/25/2021 (month/day/year) |
+| MindSpore Version | 1.1.1 |
+| Dataset | CIFAR-10 |
+| batch_size | 32 |
+| outputs | probability |
+| Accuracy | 94.02% |
+| Model for inference | 43M (.air file) |
+
+## 闅忔満鎯呭喌璇存槑
+
+> 璇存槑璇ラ」鐩湁鍙兘鍑虹幇鐨勯殢鏈轰簨浠�
+
+## 鍙傝€冩ā鏉�
+
+[maskrcnn_readme](https://gitee.com/mindspore/models/blob/master/official/cv/maskrcnn/README_CN.md)
+
+## 璐＄尞鎸囧崡
+
+濡傛灉浣犳兂鍙備笌璐＄尞鏄囨€濈殑宸ヤ綔褰撲腑锛岃闃呰[鏄囨€濊础鐚寚鍗梋(https://gitee.com/mindspore/models/blob/master/CONTRIBUTING_CN.md)鍜孾how_to_contribute](https://gitee.com/mindspore/models/tree/master/how_to_contribute)
+
+###璐＄尞鑰�
+
+-鍦ㄦ槆鑵�910涓婏紝璁粌鍜岃瘎浼伴儴鍒嗙殑宸ヤ綔璐＄尞鑰呮槸 'XXX'
+-鍦ㄦ槆鑵�910涓婏紝鎺ㄧ悊閮ㄥ垎鐨勫伐浣滆础鐚€呮槸 'XXX'
+-...
+
+## ModelZoo 涓婚〉
+
+璇锋祻瑙堝畼鏂筟涓婚〉](https://gitee.com/mindspore/models)銆�
diff --git a/how_to_contribute/README_template.md b/how_to_contribute/README_template.md
deleted file mode 100644
index 4d3046245f0b2bcd7aecdcf06d1808e0542c5bf4..0000000000000000000000000000000000000000
--- a/how_to_contribute/README_template.md
+++ /dev/null
@@ -1,99 +0,0 @@
-<TOC>
-
-# Title, Model name
-
-> The Description of Model. The paper present this model.
-
-## Model Architecture
-
-> There could be various architecture about some model. Represent the architecture of your implementation.
-
-## Features(optional)
-
-> Represent the distinctive feature you used in the model implementation. Such as distributed auto-parallel or some special training trick.
-
-## Dataset
-
-> Provide the information of the dataset you used. Check the copyrights of the dataset you used, usually don't provide the hyperlink to download the dataset.
-
-## Requirements
-
-> Provide details of the software required, including:
->
-> * The additional python package required. Add a `requirements.txt` file to the root dir of model for installing dependencies.
-> * The necessary third-party code.
-> * Some other system dependencies.
-> * Some additional operations before training or prediction.
-
-## Quick Start
-
-> How to take a try without understanding anything about the model.
-
-## Script Description
-
-> The section provide the detail of implementation.
-
-### Scripts and Sample Code
-
-> Explain every file in your project.
-
-### Script Parameter
-
-> Explain every parameter of the model. Especially the parameters in `config.py`.
-
-## Training
-
-> Provide training information.
-
-### Training Process
-
-> Provide the usage of training scripts.
-
-e.g. Run the following command for distributed training on Ascend.
-
-```shell
-bash run_distribute_train.sh [RANK_TABLE_FILE] [PRETRAINED_MODEL]
-```
-
-### Transfer Training(Optional)
-
-> Provide the guidelines about how to run transfer training based on an pretrained model.
-
-### Training Result
-
-> Provide the result of training.
-
-e.g. Training checkpoint will be stored in `XXXX/ckpt_0`. You will get result from log file like the following:
-
-```
-epoch: 11 step: 7393 ,rpn_loss: 0.02003, rcnn_loss: 0.52051, rpn_cls_loss: 0.01761, rpn_reg_loss: 0.00241, rcnn_cls_loss: 0.16028, rcnn_reg_loss: 0.08411, rcnn_mask_loss: 0.27588, total_loss: 0.54054
-epoch: 12 step: 7393 ,rpn_loss: 0.00547, rcnn_loss: 0.39258, rpn_cls_loss: 0.00285, rpn_reg_loss: 0.00262, rcnn_cls_loss: 0.08002, rcnn_reg_loss: 0.04990, rcnn_mask_loss: 0.26245, total_loss: 0.39804
-```
-
-## Evaluation
-
-### Evaluation Process
-
-> Provide the use of evaluation scripts.
-
-### Evaluation Result
-
-> Provide the result of evaluation.
-
-## Performance
-
-### Training Performance
-
-> Provide the detail of training performance including finishing loss, throughput, checkpoint size and so on.
-
-### Inference Performance
-
-> Provide the detail of evaluation performance including latency, accuracy and so on.
-
-## Description of Random Situation
-
-> Explain the random situation in the project.
-
-## ModeZoo Homepage
-
-Please check the official [homepage](https://gitee.com/mindspore/models).
\ No newline at end of file