DAB-DETR
DAB-DETR copied to clipboard
[ICLR 2022] Official implementation of the paper "DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR"
全程下载源码,coco数据集,为啥训练时候loss为20左右?
When I was training my own data set with DN-DETR, I encountered the following problems, how do I solve them? Who can tell me, please? @sorrowyn @whatchang @SlongLiu @developer0hye @rentainhe...
Could you explain why we add inverse sigmoid for the refpoint? And, when we get the output of transformer's decoder layer, we do the same thing for the refpoint. ```python...
I am trying to convert the generated model that I trained and also your pretrained model to ONNX but unfortunately I faced the following error message: RuntimeError: Expected all tensors...
Will you provide trained dab-detr models with R101 backbone and R101 DC5 backbone? Thanks a lot
hey, thanks for ur wonderful work. but here i got some problem when i read the code, 1. what is the difference between the query_pos and query_sine_embed. it seems that...
Hello, author, I used your model to train on a custom dataset. The number of objects per image in the dataset is less than 10. Is it appropriate to set...
Hi, It seems that optimizer.zero_grad() is forgotten to call [here](https://github.com/IDEA-Research/DAB-DETR/blob/79899450694fa7590a7ff2dfe242fd689abe2366/engine.py#L82-L87). Or perhaps I miss something.
Can you please convert your model into the ONNX model? I want to test it on tensor rt for inferencing. I am trying to convert it to the ONNX model...
Thanks for your great work. I have some questions about the implementation of DAB-Deformable DETR. 1. In DAB-DETR the position embedding is `sinehw`, while in DAB-Deformable-DETR it uses the original...