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

如何控制 grounding 中模型输出的 bounding box 数量 #17

Open
sleepyshep opened this issue Apr 25, 2024 · 1 comment
Open

如何控制 grounding 中模型输出的 bounding box 数量 #17

sleepyshep opened this issue Apr 25, 2024 · 1 comment

Comments

@sleepyshep
Copy link

Hi, 感谢你们开创性的工作!我注意到 CogCom 通过连接 grounding dino 实现 grouding,请问怎么控制模型输出的 bounding box 数量呢,目前模型只输出 top1 的 bounding box

@qijimrc
Copy link
Collaborator

qijimrc commented Apr 26, 2024

@sleepyshep Hi,感谢你对我们工作的关注和认可。在CoM训练数据构造阶段,我们基于GroundingDINO来识别manipulation指定的object的多个boxes;在模型推理阶段,我们直接让CogCoM输出指定object的多个boxes,以[[x1,y1,x2,y2],[x1,y1,x2,y2]]的形式表示(如果该object存在多个框且模型输出正确)。 如果输出遗漏了boxes,可能是CogCoM识别失败导致,方便的话可以share一下你的case我进行测试。

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