-
Notifications
You must be signed in to change notification settings - Fork 6
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
i want to know the parameters about ddq-detr-4scale can you tell me because ican not get the answers from your paper #23
Comments
Sorry for the late response, you may want this, it is in another branch of this repo, please check out the first DDQ DETR is also integrated into the official repo of mmdetection. |
so you still not tell me the parameters that i want to konw can you tell me?
…---Original---
From: "Shilong ***@***.***>
Date: Wed, Sep 11, 2024 19:20 PM
To: ***@***.***>;
Cc: ***@***.******@***.***>;
Subject: Re: [jshilong/DDQ] i want to know the parameters aboutddq-detr-4scale can you tell me because ican not get the answers from yourpaper (Issue #23)
Sorry for the late response, you may want this, it is in another branch of this repo, please check out the first
https://github.com/jshilong/DDQ/blob/ddq_detr/projects/configs/ddq_detr/ddq-detr-4scale_r50_8xb2-12e_coco.py
DDQ DETR is also integrated into the official repo of mmdetection.
https://github.com/open-mmlab/mmdetection/tree/main/configs/ddq
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>
|
i use the tools from mmdet and notice that the parameters is above 47.53M is that correct??
…---Original---
From: "Shilong ***@***.***>
Date: Wed, Sep 11, 2024 19:20 PM
To: ***@***.***>;
Cc: ***@***.******@***.***>;
Subject: Re: [jshilong/DDQ] i want to know the parameters aboutddq-detr-4scale can you tell me because ican not get the answers from yourpaper (Issue #23)
Sorry for the late response, you may want this, it is in another branch of this repo, please check out the first
https://github.com/jshilong/DDQ/blob/ddq_detr/projects/configs/ddq_detr/ddq-detr-4scale_r50_8xb2-12e_coco.py
DDQ DETR is also integrated into the official repo of mmdetection.
https://github.com/open-mmlab/mmdetection/tree/main/configs/ddq
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>
|
I thought you were referring to the training hyperparameters :( |
thanks
…---Original---
From: "Shilong ***@***.***>
Date: Wed, Sep 11, 2024 19:31 PM
To: ***@***.***>;
Cc: ***@***.******@***.***>;
Subject: Re: [jshilong/DDQ] i want to know the parameters aboutddq-detr-4scale can you tell me because ican not get the answers from yourpaper (Issue #23)
I thought you were referring to the training hyperparameters :(
The parameters should be at a similar level to DINO. I don’t have the machine or environment to test the specific parameters now.
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>
|
No description provided.
The text was updated successfully, but these errors were encountered: