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

How do I fine-tune a model using my own datasets in Automatic Labeling( RAM or Tag2Text ) #536

Open
leershavin opened this issue Nov 25, 2024 · 1 comment

Comments

@leershavin
Copy link

The pth file of DINO has been trained and fine-tuned, and it can be called normally under the keyword prompt mode.

Now I want to use Tag2Text or RAM’s full automatic annotation. Do I need to retrain and fine-tune? If so, can you provide the method for training and fine-tuning?

@ShuoShenDe
Copy link
Contributor

Hi dear, If you want to use Tag2Text or RAM’s full automatic annotation and it meets your data requirements, there's no need to retrain or fine-tune the model. However, if the current solutions do not fully meet your needs, you may consider fine-tuning.

While official fine-tuning guidelines are not provided, some teams have developed their own solutions. You can explore these approaches by referring to the relevant repositories, such as this one: MMDetection Grounding DINO.

Susan Shen

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