Skip to content

[Dataset] Support GID dataset on project #3038

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

Conversation

AI-Tianlong
Copy link
Contributor

Motivation

Support GID dataset on project

Copy link
Collaborator

Choose a reason for hiding this comment

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

select15imgFromAll.py
请问这个脚本会用在哪呢

Copy link
Contributor Author

Choose a reason for hiding this comment

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

在文献 MACU-Net for Semantic Segmentation of Fine-Resolution Remotely Sensed Images 中,用了 15张 图像作为数据集,并划分了训练和验证集,这个脚本是从150张图像中选择出和文献相同名称的15张图像,也可以不提供这个脚本。那么就需要使用GID数据集的社区同学自己从 150 张图像中去挑选这15张了。

Copy link
Collaborator

Choose a reason for hiding this comment

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

okok, 那可以放到 tools 里面,然后加个 docstring 说明一下这个脚本的作用 :)

Copy link
Contributor Author

Choose a reason for hiding this comment

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

okeyyy~💙

Comment on lines 37 to 38
dest_img_dir = r'D:\ATL\AI_work\Datasets\GID\15\images'
dest_label_dir = r'D:\ATL\AI_work\Datasets\GID\15\labels'
Copy link
Collaborator

Choose a reason for hiding this comment

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

这个路径不是很通用,建议改用相对路径

Copy link
Contributor Author

Choose a reason for hiding this comment

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

或许,可以修改成命令行参数的输入方式😀,当时只是想方便挑选出15张图像做复现,没有考虑的那么完善,我尽快修改

RGB_label = RGB_label.astype('int32')
idx = (RGB_label[:, :, 0] * 256 +
RGB_label[:, :, 1]) * 256 + RGB_label[:, :, 2]
# print(idx.shape)
Copy link
Collaborator

Choose a reason for hiding this comment

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

可以删掉这些 debug 用的注释

Copy link
Contributor Author

Choose a reason for hiding this comment

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

收到~

AI-Tianlong and others added 4 commits May 30, 2023 10:28
Co-authored-by: 谢昕辰 <xiexinch@outlook.com>
…om:AI-Tianlong/mmsegmentation into AI-Tianlong/Support_GID_dataset_On_Project
@xiexinch xiexinch merged commit e5b8d72 into open-mmlab:dev-1.x Jun 5, 2023
nahidnazifi87 pushed a commit to nahidnazifi87/mmsegmentation_playground that referenced this pull request Apr 5, 2024
## Motivation
Support GID dataset on project

---------

Co-authored-by: 谢昕辰 <xiexinch@outlook.com>
@Momo-coder1
Copy link

你好,可以加下联系方式吗?关于gid数据集有点问题想请教

@AI-Tianlong
Copy link
Contributor Author

您可以直接在这里问呢 @Momo-coder1

@Momo-coder1
Copy link

@AI-Tianlong 按照你的方法划分好数据集训练时,Forest类别指标一直显示nan

@AI-Tianlong
Copy link
Contributor Author

@Momo-coder1 ,是否能提供更详细的数据呢?
准确来说,GID数据集有150景GF2影像,进行裁切测试时,仅选取了部分进行测试。理论上,需要将150景影像划分为训练集和验证集,能否提供您的训练结果以及配置文件呢?

@Momo-coder1
Copy link

20250323_120654.log
@AI-Tianlong 你的意思是说你选取的15张图片中没有Forest这个类吗?得把150张图片全部裁切测试?

@AI-Tianlong
Copy link
Contributor Author

@Momo-coder1 是的,需要对150张全部进行处理。教程只提供了小样本的测试,看起来其他类别都没有问题,训练集图片的裁切应该是都没有问题的。估计还是数据的问题,可以可视化下看看,是否包含。
而且如果只有5张图像作为验证集的话。。。大概率类别不全

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

Successfully merging this pull request may close these issues.

3 participants
pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy