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

Any tips for finetuning on private datasets? #16

Open
alen-mask opened this issue Dec 20, 2019 · 2 comments
Open

Any tips for finetuning on private datasets? #16

alen-mask opened this issue Dec 20, 2019 · 2 comments

Comments

@alen-mask
Copy link

Hi @PKUbahuangliuhe ,

Great work! So fay as i know, cbnet is the sota on coco object detection tasks.
Do you have any plans to support finetuning on other datasets(different number of object classes) from your pretrained model?
Any tips or reference code here?

Many thanks!

@PKUbahuangliuhe
Copy link
Collaborator

Hi @PKUbahuangliuhe ,

Great work! So fay as i know, cbnet is the sota on coco object detection tasks.
Do you have any plans to support finetuning on other datasets(different number of object classes) from your pretrained model?
Any tips or reference code here?

Many thanks!

you can convert the format of your data to COCO.Note that the number class should also be modified,and just train it.

@alen-mask
Copy link
Author

Hi @PKUbahuangliuhe ,
Great work! So fay as i know, cbnet is the sota on coco object detection tasks.
Do you have any plans to support finetuning on other datasets(different number of object classes) from your pretrained model?
Any tips or reference code here?
Many thanks!

you can convert the format of your data to COCO.Note that the number class should also be modified,and just train it.

Thanks very much, guess i should read the training code again.

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

2 participants