Rotated_IoU

Rotated_IoU copied to clipboard

a problem when using 3d-giou for regression training

2

Hello,There is a problem when using 3d-giou for regression training. When I use 3d-giou to train 3dssd on my own dataset(5 classes: car perdestrian headstock fulltrailer emptytrailer), it seems that...

Gretacyh

debug版本报错

3

 我不知道错在哪里喃

LUO77123

warning: missing return statement at end of non-void function "compare_vertices"

6

大佬，我在本地运行就可以，一到服务器上，就显示这个warning: missing return statement at end of non-void function "compare_vertices"，还是可以install，但是运行起来就全部是nan

LUO77123

Wrong IoU calculation when corners are smaller than 0

6

Hi! Thank you @lilanxiao for your great work. I have been using your work for sometime, and it has been beneficial for my training. One problem I encountered was under...

Eralien

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

7


c978899

Inaccurate IoU in some cases

8

Hi, this repo is very useful for me! But when I test for the accuracy, I find in one case the result of oriented_box_intersection_2d is wrong. box1 = [4,5,8,10,0] box2...

JarvisUSTC

is this result correct?

2

``` import Rotated_IoU.oriented_iou_loss as ri import torch import numpy as np import math box1 = torch.tensor([[[0.,0.,2.,2.,torch.pi/4]]]).to("cuda") iou,_,_,_ = ri.cal_iou(box1, box1) print(iou) ``` above iou value is "0." but when i...

sang0775

Is it possible to apply this to YOLACT? How might i go about doing so?

Mogarbobac

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]

1

我尝试在维基百科上查找了另外一种算法(叉积)， 重写了此函数，是我对函数的理解有错误？或者你提供的原始的函数存在bug? 你有什么修正的建议吗？ * 原始代码 ```python def box1_in_box2(corners1:torch.Tensor, corners2:torch.Tensor): a = corners2[:, :, 0:1, :] # (B, N, 1, 2) b = corners2[:, :, 1:2, :] # (B, N, 1,...

XiaoyanQian

我能运行demo，但自己import oriented_iou_loss时会出现找不到包

Liming1737