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.

Sign up for GitHub

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

Jump to bottom

[Doc] Chinese translation of Inpainting datasets #666

Merged
merged 2 commits into from
Dec 21, 2021
Merged

[Doc] Chinese translation of Inpainting datasets #666

merged 2 commits into from
Dec 21, 2021

Conversation

ckkelvinchan
Copy link
Member

No description provided.

@codecov
Copy link

codecov bot commented Dec 18, 2021 •
edited
Loading

Codecov Report

Merging #666 (8069ea0) into master (34d39c8) will increase coverage by 0.17%.
The diff coverage is n/a.

Impacted file tree graph

@@            Coverage Diff             @@
##           master     #666      +/-   ##
==========================================
+ Coverage   80.49%   80.67%   +0.17%     
==========================================
  Files         198      199       +1     
  Lines       11234    11371     +137     
  Branches     1795     1818      +23     
==========================================
+ Hits         9043     9173     +130     
  Misses       1915     1915              
- Partials      276      283       +7
Flag Coverage Δ
unittests 80.64% <ø> (+0.16%) ⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files Coverage Δ
mmedit/models/restorers/__init__.py 100.00% <0.00%> (ø)
mmedit/datasets/pipelines/__init__.py 100.00% <0.00%> (ø)
mmedit/models/restorers/real_basicvsr.py 87.01% <0.00%> (ø)
mmedit/datasets/pipelines/crop.py 97.24% <0.00%> (+0.20%) ⬆️
mmedit/datasets/pipelines/random_degradations.py 94.68% <0.00%> (+0.79%) ⬆️
...ls/components/stylegan2/generator_discriminator.py 86.14% <0.00%> (+1.20%) ⬆️
...edit/models/components/discriminators/unet_disc.py 87.50% <0.00%> (+2.08%) ⬆️

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 34d39c8...8069ea0. Read the comment docs.

wangruohui
wangruohui reviewed Dec 20, 2021
View reviewed changes
Copy link
Member

@wangruohui wangruohui left a comment

Choose a reason for hiding this comment

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

some improvements are provided for reference

tools/data/inpainting/README_zh-CN.md
@@ -1 +1,25 @@
# 数据集 - 补全
Copy link
Member

Choose a reason for hiding this comment

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

建议inpainting翻译为 图像修复 或图像补全

Copy link
Member

Choose a reason for hiding this comment

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

后续关于inpainting的翻译需要保持统一

tools/data/inpainting/README_zh-CN.md Outdated
* [CelebA-HQ](celeba-hq/README.md) \[ [主页](https://github.com/tkarras/progressive_growing_of_gans#preparing-datasets-for-training) \]
* [Places365](places365/README.md) \[ [主页](http://places2.csail.mit.edu/) \]

由于我们只需要用于补全任务的图像，因此不需要进一步准备，而且文件夹结构亦可以与示例不同。您可以利用原始数据集提供的信息，如 `Place365` （例如 `meta` ）。此外，您亦可以轻松扫描数据集并将所有图像列出到特定的 `txt` 文件中。 以下是 Places365 中的 `Places365_val.txt` 的示例，我们将仅在补全中使用图像名称信息。
Copy link
Member

Choose a reason for hiding this comment

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

As we only need images for inpainting task, further preparation is not necessary and the folder structure can be different from the example.
由于在图像修复任务中，我们只需要使用图像，因此我们不需要对数据集进行额外的预处理操作，文件目录的结构也可以和本例有所不同。

You can utilize the information provided by the original dataset like Place365 (e.g. meta).
这段问题不大

Also, you can easily scan the data set and list all of the images to a specific txt file.
或者，您可以直接遍历数据集文件夹，并将所有图像文件的路径罗列在一个文本文件中。

Here is an example for the Places365_val.txt from Places365 and we will only use the image name information in inpainting.
下面的例子节选自 Places365 数据集中的 Places365_val.txt ，针对图像修复任务，我们只需要使用其中的文件名信息。

tools/data/inpainting/places365/README_zh-CN.md Outdated
@@ -12,3 +12,19 @@
}

```

请从 [Places365](http://places2.csail.mit.edu/download.html) 准备数据。
Copy link
Member

Choose a reason for hiding this comment

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

请从 places365 下载并准备数据

@ckkelvinchan ckkelvinchan merged commit 13e51b4 into open-mmlab:master Dec 21, 2021
Yshuo-Li pushed a commit to Yshuo-Li/mmediting that referenced this pull request Jul 15, 2022
@ckkelvinchan
[Doc] Chinese translation of Inpainting datasets (open-mmlab#666)
ff0c655
Yshuo-Li pushed a commit to Yshuo-Li/mmediting that referenced this pull request Jul 15, 2022
@ckkelvinchan
[Doc] Chinese translation of Inpainting datasets (open-mmlab#666)
156594b
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@wangruohui wangruohui wangruohui left review comments

@Yshuo-Li Yshuo-Li Yshuo-Li approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@ckkelvinchan @wangruohui @Yshuo-Li