-
### Checklist
- The object-loss, the bbox-loss and the classification loss can be shown on the output log, but the Channel Wise Divergence loss seems not been calculated during training
### Des…
-
### 问题描述 Please describe your issue
PP-YOLOE有没有试验过SIoU Loss(SCYLLA-IoU Loss)？该损失函数号称在COCO数据集上涨点2.4-3.6，论文：https://arxiv.org/pdf/2205.12740.pdf
 and [Discussions](https://github.com/open-mmlab/mmdetection3d/discussions) but cannot get the exp…
-
Hi I tried to run the introduced model using MVtec dataset according to READ.ME, but I got the following error in detection.py. I don't know how to solve this problem. Please help me to solve this pro…
-
### Prerequisite
- [X] I have searched [Issues](https://github.com/open-mmlab/mmdetection3d/issues) and [Discussions](https://github.com/open-mmlab/mmdetection3d/discussions) but cannot get the expec…
-
Hi! At first, thanks for your excellent work! It's a really impressive and ideal modeling method for HD Map elements. I'm also tring to follow your work and there are some questions about it. I'm appr…
-
GIT COMMIT ID: 0371cf6f9411d410ed4b4bb02becea23677da1ff
CPU: Intel(R) Core(TM) i7-9700 CPU @ 3.00GHz
系统环境: Ubuntu18.04 Anaconda:python37
安装方式: 本地编译
命令:
git clone https://github.com/paddlepaddle/…
-
## 🚀 Feature
Implement Distance and Complete IoU within torchvision to complement the current supported implementations of IoU and GIoU
## Motivation
Distance and Complete IoU have been published…
-
### 🐛 Describe the bug
`*box_iou()` functions should return a matrix of results for every possible pair (box1, box2), where box1 is a box from `boxes1` and box2 is a box from `boxes2`. `box_iou()` …