-
### Question
作者你好，关于论文中“5.4 Transferability of position relation”中Relation编码实现了对三种detr变体的性能提升，请问可以开源这三个detr变体的实现代码吗。谢谢！
### 补充信息
_No response_
-
### Question
大佬您好，最近拜读了你的Relation DETR 收获很多，现在有几个问题想请教一下：
1.在论文图1中，您用MC指标展示了不同数据集下目标框的位置关系，以此说明位置的统计意义。可以发现特定任务数据集的指标更靠右。我想问下是否意味着您这种方法更适合用于特定数据集呢？您是否在ESD、CSD、MSSD这些数据集上试验过呢，提升会更明显吗？
2.公式8中为何要使用M…
-
### Question
Hi @xiuqhou,
Niels here from the open-source team at Hugging Face. I discovered your work through a paper that builds on your framework: https://huggingface.co/papers/2407.11699. I wo…
-
### Bug
训练正常，但是使用`inference.py`推理或者转换ONNX时报错：
```
Traceback (most recent call last):
File "/home/code/Relation-DETR/inference.py", line 165, in
inference()
File "/home/user/code/Relati…
-
### Question
Hey,
are you planning to release the models of Salience-DETR and Relation-DETR also on Huggingface? I see that you have already published the dataset there :) Would be great for easy …
-
### Question
In Relation DETR, is the VFL loss the same as the vari_sigmoid_focal_loss function?
### Additional
_No response_
-
In paper:
```We propose a novel lightweight relation extractor, EGTR, which exploits the self-attention of DETR decoder, as depicted in Fig. 3. Since the self-attention weights in Eq. (1) contain N ×…
-
### Question
Thanks again for your research! The position relation idea is very smart. I've had success improving DINO/ DDQ / Align DETR baselines with Relation DETR for images with 1500 objects, e.g…
-
### Question
Hi, Thanks for the awesome repo. I am trying to finetune your model on a custom dataset. My GPU memory is not enough to finetune relation_detr_focalnet_large_lrf_fl4_1200_2000.py version…
-
### Bug
Traceback (most recent call last):
File "D:\BaiduNetdiskDownload\Relation-DETR-main\main.py", line 213, in
train()
File "D:\BaiduNetdiskDownload\Relation-DETR-main\main.py", line …