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

what about custom dataset training? #3

Open
orkunozturk opened this issue Aug 24, 2022 · 3 comments
Open

what about custom dataset training? #3

orkunozturk opened this issue Aug 24, 2022 · 3 comments

Comments

@orkunozturk
Copy link

Hi, thanks for your work.

I wonder how can i train and test on my custom dataset. Should i create reference annotation data? Can you share the related script to generate this file?

@saswat0
Copy link

saswat0 commented Oct 29, 2022

Hi @hero-y
It'd be great if you could share the above script or explain its significance.

@hero-y
Copy link
Owner

hero-y commented Feb 8, 2023

Hi, I don't try our method on the custom dataset, but I think it isn't difficult. First, you should prepare your custom dataset with the coco format. Then, you don't need to prepare the ref_ann_file (refer to voc config). If the ref_ann_file doesn't exist, the code will choose one class-object annotation from the whole annotation as the reference (refer to datasets/one_shot_voc).

@szgy66
Copy link

szgy66 commented Jun 12, 2023

Hi, thanks for your work.

I wonder how can i train and test on my custom dataset. Should i create reference annotation data? Can you share the related script to generate this file?

Hello, Had you train and test on your custom dataset?

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

4 participants