Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Docs] Add Chinese version of customize_models.md #27

Merged
merged 6 commits into from
Feb 26, 2022
Merged

[Docs] Add Chinese version of customize_models.md #27

merged 6 commits into from
Feb 26, 2022

Conversation

Abyssaledge
Copy link
Contributor

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.

Motivation

Add Chinese version customize_models.md

Modification

Add Chinese version customize_models.md

BC-breaking (Optional)

Does the modification introduce changes that break the back compatibility of the downstream repos?
No

Use cases (Optional)

Checklist

  1. Pre-commit or other linting tools are used to fix the potential lint issues.
  2. The modification is covered by complete unit tests. If not, please add more unit test to ensure the correctness.
  3. The documentation has been modified accordingly, like docstring or example tutorials.

@zytx121
Copy link
Collaborator

zytx121 commented Feb 23, 2022

Hi @Abyssaledge
Please fix the lint first.
You can refer to https://github.com/open-mmlab/mmcv/blob/master/CONTRIBUTING.md for proper use of pre-commit.

@Abyssaledge
Copy link
Contributor Author

@zytx121 Thanks for reminding, I believe the linting problem is fixed now.

- loss: the component in head for calculating losses, e.g., FocalLoss, GWDLoss, and KFIoULoss.
- 主干网络 (Backbone): 通常是一个全卷积网络 (FCN),用来提取特征图,比如残差网络 (ResNet)。也可以是基于视觉 Transformer 的网络,比如 Swin Transformer 等。
- Neck: 主干网络和任务头 (Head) 之间的连接组件,比如 FPN, ReFPN。
- 任头务 (Head): 用于某种具体任务(比如边界框预测)的组件。
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

任务头


Create a new file `mmrotate/models/backbones/mobilenet.py`.
新建文件 `mmrotate/models/backbones/mobilenet.py`.
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

最后的标点可以用中文的句号


Create a new file `mmrotate/models/necks/pafpn.py`.
新建文件: `mmrotate/models/necks/pafpn.py`.
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

这里的冒号可以省略,最后的句号也可以改为中文句号。

First, add a new bbox head in `mmrotate/models/roi_heads/bbox_heads/double_bbox_head.py`.
Double Head R-CNN implements a new bbox head for object detection.
To implement a bbox head, basically we need to implement three functions of the new module as the following.
首先,添加一个新的 bbox head 到 `mmrotate/models/roi_heads/bbox_heads/double_bbox_head.py`.
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

这里也可以使用中文句号。


```python
custom_imports=dict(
imports=['mmrotate.models.roi_heads.double_roi_head', 'mmrotate.models.bbox_heads.double_bbox_head'])
```

to the config file and achieve the same goal.
到配置文件中来实现同样的功能.
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

中文句号

@Abyssaledge
Copy link
Contributor Author

@jbwang1997 感谢提醒,标点问题已经修改。

Copy link
Collaborator

@jbwang1997 jbwang1997 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

我这里没有什么问题了。

@jbwang1997
Copy link
Collaborator

Kindly ping @zytx121 to have a look.

Copy link
Collaborator

@yangxue0827 yangxue0827 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
Development

Successfully merging this pull request may close these issues.

None yet

5 participants