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

Training RT-DETR with custom dataset #8293

Open
1 task done
viethoang303 opened this issue May 29, 2023 · 2 comments
Open
1 task done

Training RT-DETR with custom dataset #8293

viethoang303 opened this issue May 29, 2023 · 2 comments
Assignees
Labels
question Further information is requested rtdetr

Comments

@viethoang303
Copy link

问题确认 Search before asking

  • 我已经搜索过问题,但是没有找到解答。I have searched the question and found no related answer.

请提出你的问题 Please ask your question

Hi authors,
I am interested in RT-DETR, and I want to run code to train model but I don't know format of dataset for dataloader. Does it have to have the same format as COCO ?
Thank you

@viethoang303 viethoang303 added the question Further information is requested label May 29, 2023
@lyuwenyu
Copy link
Collaborator

Your can train rtdetr on your data following below two steps:

  1. Prepare your data as coco format, PrepareDetDataSet
  2. Modify default dataset config, coco_detection

@viethoang303
Copy link
Author

viethoang303 commented May 30, 2023

@lyuwenyu Thank you very much, I have just run my code but when I set "export CUDA_VISIBLE_DEVICES=1", the code access to gpu 0 not gpu 1. So how to fix this?

Your can train rtdetr on your data following below two steps:

  1. Prepare your data as coco format, PrepareDetDataSet
  2. Modify default dataset config, coco_detection

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
question Further information is requested rtdetr
Projects
None yet
Development

No branches or pull requests

2 participants