Skip to content

Dataset preparation for Object Detection with Florence2 #1977

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

Closed
Mistsink opened this issue Sep 8, 2024 · 9 comments
Closed

Dataset preparation for Object Detection with Florence2 #1977

Mistsink opened this issue Sep 8, 2024 · 9 comments

Comments

@Mistsink
Copy link

Mistsink commented Sep 8, 2024

准备微调Florence2的目标检测任务,目前只有一个类,但是一张图片可能有多个框需要检测到,请问我的数据集应该造成什么格式的呢?应该是需要构造一个jsonl文件吧?😂非常感谢!

@tastelikefeet
Copy link
Collaborator

@Mistsink
Copy link
Author

Mistsink commented Sep 9, 2024

这个感觉并没有很好的帮助呢。文档中给出了Caption和Grounding的示例数据集,但还是也不清楚我这种针对指定类进行目标检测的数据集应该是什么格式的呢?而且还是针对Florence2这个模型。如果您方便的话可以麻烦给我举个例子吗?比如一张图片中有三只猫和两条狗需要被检测到,jsonl文件的内容应该是什么样的呢?
image

@lyf6
Copy link

lyf6 commented Sep 26, 2024

@Mistsink 请问你解决了吗

@taylover-pei
Copy link

@Mistsink 你好解决了吗?能否给个例子?

@Mistsink
Copy link
Author

兄弟们别问了,并没有解决,我直接放弃了

@tastelikefeet
Copy link
Collaborator

tastelikefeet commented Feb 21, 2025

@Mistsink
Copy link
Author

好滴,让他俩试试吧,我已然是退出这个赛道了 hhhh

@tastelikefeet
Copy link
Collaborator

好滴,让他俩试试吧,我已然是退出这个赛道了 hhhh

居然过去了半年之久。。。可以加一下我们答疑群,那个里面的问题回答实时性更高些,有时候忙忘了就注意不到之前的issue了[手动捂脸]

@taylover-pei
Copy link

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

No branches or pull requests

5 participants