jbwang1997 / aopg

Anchor-free Oriented Proposal Generator for Object Detection

• 🔭 I am currently a second-year Ph.D. student in College of Computer Science at Nankai University, under the supervision of Prof. Mingming Cheng and Prof. Qibin Hou. Earlier, I obtained my M.S. degree, in School of Automation at Northwestern Polytechnical University, under the supervision of Prof. Junwei Han and Proj. Gong Cheng.

• 👁️ My research interests cover a range of topics in computer vision and machine learning, such as 2D/3D/oriented object detection and 3D perception in autonomous driving. I'm Currently learning the knowledge about image synthesis. For more details, please refer to my google scholar and homepage.

• 📫 You are very welcome to contact me regarding my research. I can be contacted directly at [email protected].

Here are some stats about my github

$~$

aopg's Issues

Dior-R

作者 你好，这个链接指向的数据集 我看了是dior数据集 Annotations好像都是水平标注框。没有旋转框啊？在哪里获取到旋转框数据然后再用AOPG进行训练和测试呢？谢谢。

improved mAP on my run

I've trained the AOPG using aopg_r50_fpn_1x_dior config on DIOR-R and received 0.66 mAP on the test set.
The only change I've done is the use of CUDA 11 and the migration of the cuda ext (mmdet/ops/) from the THC to ATen (in order it to run on cuda 11.
This is an increase from the 64.41 mAP published on your paper.
I've trained on trainval set and tested on test set.
Does this improvement in mAP make sense?

关于文章中DIOR-R的结果咨询。

请问文章中关于DIOR-R的实验结果是VOC07还是VOC12，另外数据增强只有水平和垂直翻转吗？

权重文件

作者您好！我用DOTA1.0数据集训练12轮跑出来的结果差了两个点，代码git下来后我没有动过，您知道可能是什么原因吗？

Maybe a little error in Code

AOPG/mmdet/models/dense_heads/obb/aopg_head.py

Line 79 in 77169f2

self.conv_shape = nn.Conv2d(self.in_channels, 4, 1)

From line 79 to 82, the first parameter of Conv2D 'self.in_channels' should be 'self.feat_channels'.

I don't know *

• means the results from AerialDetection. what is meaning with it?

在huge_image_demo代码里面出现了一个遗漏，显示不出图片

在最后的result的信息没有赋值给img，导致了出现的还是原来的图片，不是检测后的图片

关于在HRSC上验证不了事宜

给尊敬的西工大课题组问好！
我发现在HRSC上不能进行验证（在DOTA上可验证），一验证就报错（AttributeError: 'ConfigDict' object has no attribute 'test'），训练时加上验证同样报错（IndexError: tuple index out of range）。作者你那边有这个问题吗？

模型调不通

configs/obb/aopg/aopg_r50_fpn_3x_hrsc.py代码中缺少相应文件，希望得到您的回复

测试时报错，请问是不是评估文件的事？

loss configs file

Thanks for your error report and we appreciate it a lot.

Checklist

1. I have searched related issues but cannot get the expected help.
2. The bug has not been fixed in the latest version.

Describe the bug
A clear and concise description of what the bug is.

Reproduction

1. What command or script did you run?

A placeholder for the command.

2. Did you make any modifications on the code or config? Did you understand what you have modified?
3. What dataset did you use?

Environment

1. Please run python mmdet/utils/collect_env.py to collect necessary environment infomation and paste it here.
2. You may add addition that may be helpful for locating the problem, such as
   • How you installed PyTorch [e.g., pip, conda, source]
   • Other environment variables that may be related (such as $PATH, $LD_LIBRARY_PATH, $PYTHONPATH, etc.)

Error traceback
If applicable, paste the error trackback here.

A placeholder for trackback.

Bug fix
If you have already identified the reason, you can provide the information here. If you are willing to create a PR to fix it, please also leave a comment here and that would be much appreciated!

How to get the DIOR-R from DIOR?Can't acheive the 80.66map?

repo里得DIOR下载链接只能下载DIOR，怎么获得DIOR-R？我用repo里得demo跑了一遍只能达到79.80，为什么会差了一个点？

-

.

请问RTX3090，CUDA11编译报错该怎么解决

RTX3090，CUDA11的环境下，mmpycocotools无法编译，mmcv只能安装1.3+
请问是否需要修改代码，有没有解决方法，或者有没有相关的教程链接让我学一学
非常希望您的帮助，谢谢