-
Notifications
You must be signed in to change notification settings - Fork 566
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
Roadmap of MMRotate #1
Comments
I am down to help! |
Is there any plan for Rotated IoU Loss or Poly IoU Loss, it can easily improve detector performance. But both of them need cuda ops, i can help with python code, but I don't know much about cuda code. =.= |
Any plan for applying oriented bbox to instance segmentation? |
can you also make the mmrotate implementation of PIoU loss ? |
Will you add anchor-free model in furture? Maybe a few month later? |
|
I get it.Thanks. But I have another question to ask. Will your team has plan to finish CenterNet or FCOS e.g. in a few month later?
…------------------ 原始邮件 ------------------
发件人: ***@***.***>;
发送时间: 2022年3月30日(星期三) 晚上9:30
收件人: ***@***.***>;
抄送: ***@***.***>; ***@***.***>;
主题: Re: [open-mmlab/mmrotate] Roadmap of MMRotate (Issue #1)
rotated_reppoints is a anchor free detector.
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: ***@***.***>
|
Yes, we will. FCOS is on the way, done by @liuyanyi |
Thanks for your reply. Your work are amzing. You'll hear this a lot, but I'm telling you, every time I look at the code, it's a wow.
…------------------ 原始邮件 ------------------
发件人: ***@***.***>;
发送时间: 2022年3月30日(星期三) 晚上9:39
收件人: ***@***.***>;
抄送: ***@***.***>; ***@***.***>;
主题: Re: [open-mmlab/mmrotate] Roadmap of MMRotate (Issue #1)
Yes, we will. FCOS is on the way, done by @liuyanyi
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: ***@***.***>
|
@zytx121 @yangxue0827 Could you please add Darknet53 as backbone (from YOLOv4) and YOLO as detector? |
sorry,I don't know your meaning.
…------------------ 原始邮件 ------------------
发件人: "Addie Ira B. ***@***.***>;
发送时间: 2022年4月27日(星期三) 中午1:37
收件人: ***@***.***>;
抄送: ***@***.***>; ***@***.***>;
主题: Re: [open-mmlab/mmrotate] Roadmap of MMRotate (Issue #1)
Could you please add Darknet53 as backbone?
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: ***@***.***>
|
Pls add Masks in MMRotate |
Please support onnx/trt export. |
I noticed it stated as supported in the paper - really confusing: |
Is there a plan to add 2022 CVPR “Oriented RepPoints for Aerial Object Detection”? |
mmdet.datasets.pipelines.test_time_aug |
+1 for onnx conversion |
onnx转换为+2 |
'OrientedRepPointsHead is already registered in models,情况该如何解决啊 |
Hi, I was wondering if there is any releases planned? There haven't been major updates for a while, and just curious if you guys are still actively developing |
Hi, can we have yolov8 for Oriented Object Detection ? |
|
We keep this issue open to collect feature requests from users and hear your voice. Our monthly release plan is also available here.
You can either:
Suggest a new feature by leaving a comment.
Vote for a feature request with 👍 or be against with 👎. (Remember that developers are busy and cannot respond to all feature requests, so vote for your most favorable one!)
Tell us that you would like to help implement one of the features in the list or review the PRs. (This is the greatest things to hear about!)
We also released our TODO list on the project page. Most of the TODO items are described in their corresponding issues (those labeled by Dev-RD) with detailed requirement documentation. Feel free to leave a message in the issue of any item and create a PR if you are interested in any of the item.
The text was updated successfully, but these errors were encountered: