-
in detr3d_head.py,
```
if not self.as_two_stage:
self.query_embedding = nn.Embedding(self.num_query,
self.embed_dims * 2)
`…
-
-
## ❓ How to do something using DETR
Hello All,
I am using DETR on custom data, which contains 2k images for training. I have followed your suggestion proposed in #9 to fine-tune to avoid gettin…
-
Hi,
Thank you for the sharing. I replaced the DETR's encoder MultiHeadAtten with SimA, it works pretty well. I am wondering is it possible to replace the cross attention in decoder? If so, any clu…
-
Thanks for your error report and we appreciate it a lot.
**Describe the bug**
I want to train CO-DETR with my own dataset, but I encountered an error:
```
Traceback (most recent call last):
F…
-
Hi,
I'm trying to build my own dataset that would work with DETR. I'm a bit confused on the data format that the matcher expects to perform the matching.
From the comment https://github.com/face…
-
**Thanks your Great Work**
是否可以提供onnx和pytorch版本模型对应的推理时间或fps，最终trt版本的推理速度和论文没法对齐，想逐步排查问题所在
-
Sorry to bother you.The error message is as follows. How can I resolve it？
root@i-r5mjznu9:/workspace/cbn/DINO# /opt/conda/lib/python3.8/site-packages/torch/tensor.py:559: UserWarning: floor_divide i…
cbn3 updated
11 months ago
-
已从源码安装：
pip show MultiScaleDeformableAttention
Name: MultiScaleDeformableAttention
Version: 1.0
Summary: PyTorch Wrapper for CUDA Functions of Multi-Scale Deformable Attention
Home-page: https://…
cjl09 updated
7 months ago
-
If you do not know the root cause of the problem, and wish someone to help you, please
post according to this template:
I have replaced the picture used as an [example](http://images.cocodataset.o…