lilanxiao Rotated_IoU issues

lilanxiao / Rotated_IoU

Differentiable IoU of rotated bounding boxes using Pytorch

MIT License

415 stars 64 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

about cuda

#56 shao-guang-yang opened 2 weeks ago
0
problems with the import of sort_vertices

#55 Innocent-Appiah opened 6 months ago
1
`np.bool` was a deprecated alias for the builtin `bool`.

#54 Uzukidd opened 8 months ago
0
Segmentation fault

#53 githigher opened 10 months ago
0
为什么input shape是 B，N，4，2？

#52 zuoningz opened 1 year ago
0
debug版本和老的版本计算结果不一致

#51 wangkang104613 opened 1 year ago
0
Batch computation for IoU Loss

#50 Steven-m2ai opened 1 year ago
3
inf bbox loss when using cal_giou_3d ( but the iou is right)

#49 YuQiao0303 opened 2 years ago
0
大佬，求助，CUDA out of memory

#48 LUO77123 opened 2 years ago
12
a problem when using 3d-giou for regression training

#47 Gretacyh opened 2 years ago
2
debug版本报错

#46 LUO77123 opened 2 years ago
3
warning: missing return statement at end of non-void function "compare_vertices"

#45 LUO77123 opened 2 years ago
6
Please Help

#44 Deerzh closed 2 years ago
1
请教大佬代码实现问题

#43 LUO77123 closed 2 years ago
2
About the 2D coordinates (x, y, w, h, alpha)

#42 KimSangYeon-DGU closed 2 years ago
2
Yolact

#41 Mogarbobac opened 2 years ago
0
Wrong IoU calculation when corners are smaller than 0

#40 Eralien opened 2 years ago
6
Inaccurate IoU in some cases

#39 JarvisUSTC opened 2 years ago
8
is this result correct?

#38 sang0775 opened 2 years ago
2
在做批量的旋转iou计算时，计算的inter_area会出现nan值，导致loss变为nan，但是在把计算为nan的两个box的x,y,w,h,angle提出来单个计算的话就会出现正常的inter_area。请问这是什么原因导致的呢，还请解答

#37 c978899 opened 2 years ago
7
box_intersection_2d 中的box1_in_box2存在bug, box1_in_box2(box1,box1), 在特定数据下返回的不是[true,true,true,true]

#36 XiaoyanQian opened 2 years ago
1
ModuleNotFoundError: No module named 'sort_vertices'

#35 Liming1737 opened 2 years ago
0
The computational cost of accurate rotated iou?

#34 colian closed 3 years ago
2
box3d的维度（x,y,z,l,w,h,alpha）

#33 XiaoyanQian opened 3 years ago
2
loss suddenly increase?

#32 jacklin602 closed 3 years ago
2
Usage on KITTI

#31 linchunmian opened 3 years ago
7
Sorting vertices is gives wrong result on different gpu

#30 alexzhou907 closed 2 years ago
2
Bug with oriented_box_intersection_2d function

#29 OneOneLiu closed 3 years ago
6
PyTorch1.2 and CUDA10.0

#28 linchunmian closed 2 years ago
6
Bug in cal_dious_3d function

#27 ShuojieMo opened 3 years ago
1
Not able to run Rotated_IoU in Spyder but works in Anaconda Prompt

#26 dominikj2 closed 3 years ago
2
Is this method can used by arbitrary polygons?

#25 liuchangf closed 2 years ago
5
ModuleNotFoundError: No module named 'sort_vertices' when run python demo

#24 jasmine202106 closed 2 years ago
6
A question about the code implementation

#23 zzybj closed 3 years ago
2
AttributeError: 'Tensor' object has no attribute 'square'

#22 Savid-mask777 closed 3 years ago
1
Box transformation

#21 WangYueFt closed 2 years ago
1
Function 'SqrtBackward' returned nan values in its 0th output. Bug in min_enclosing_box.py?

#20 zye1996 closed 3 years ago
3
Orientation Problems

#19 JonathanCMitchell closed 3 years ago
1
Bug in IOU_3d

#18 JonathanCMitchell closed 3 years ago
4
Use on KITTI dataset labels

#17 a-akram-98 opened 3 years ago
7
Minimum Bounding Box implementation Rotating Calipers

#16 JonathanCMitchell closed 3 years ago
11
Why are we sorting vertices to calculate 2D intersection?

#15 JonathanCMitchell closed 3 years ago
3
CUDA 11

#14 filaPro closed 3 years ago
1
same rotated bbox while iou == 0

#13 ucasqcz closed 3 years ago
6
Different number of labels and Prediction?

#12 zobeirraisi closed 3 years ago
2
关于参数的疑问

#11 cnexah closed 3 years ago
2
compile error

#10 FenHua closed 4 years ago
2
backpropagation when Rotate_IOU = 0

#9 JJangD closed 3 years ago
4
incorrect iou?

#8 filaPro closed 3 years ago
13
about backward function

#7 orkunozturk closed 4 years ago
3