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

Change number of objects #105

Open
ferchonavarro opened this issue Mar 22, 2024 · 5 comments
Open

Change number of objects #105

ferchonavarro opened this issue Mar 22, 2024 · 5 comments

Comments

@ferchonavarro
Copy link

The default value is to output 100 objects (for all classes)
How can I change it to output more objects for instance 300.
What do I have to change in the config or code to get this?

@ferchonavarro
Copy link
Author

Did you have aa change to look at my question?
Thanks in advance.

@ferchonavarro
Copy link
Author

@FengLi-ust

I have tried to modify the config to change the number of predicted objects from default 100 to 300

I have tried NUM_OBJECT_QUERIES: 300 and DN_NUM: 300 nevertheless the output is still 100xh,w

Could you point me to the config parameters to change to be able to change the number of predicted objects?

@Small-fly-guy
Copy link

May I ask if you succeeded, my dataset has only one class, I tried to change NUM_OBJECT_QUERIES to 1 and it ran successfully but I'm not sure if it's right or not!

@ferchonavarro
Copy link
Author

@Small-fly-guy the NUM_OBJECT_QUERIES is not related to the number of classes. NUM_OBJECT_QUERIES refers to how many max objects are present in your image, I would not set this to 1 The number of classes will be get from your COCO dataset format.

@FengLi-ust
Copy link
Collaborator

Sorry for the late reply. Can you give more details about changing NUM_OBJECT_QUERIES?

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

3 participants