Co-DETR icon indicating copy to clipboard operation
Co-DETR copied to clipboard

[ICCV 2023] DETRs with Collaborative Hybrid Assignments Training

Results 109 Co-DETR issues
Sort by recently updated
recently updated
newest added

本地化配置过程中遇到报错ModuleNotFoundError: No module named 'projects' 不知应该如何解决?

![image](https://github.com/Sense-X/Co-DETR/assets/129565713/1bcaca0f-ed1c-4756-9374-90fd2e22ec43) When running the command: sh tools/dist_test. sh projects/configs/co-deformable_detr/co-deformable_detr_r50_1x_coco. py path_to_checkpoint 8-- eval bbox, error: ModuleNotFoundError: No module named 'mmdet. registry' Environment configuration: Python=3.11, pytorch=1.11.0, cuda=11.3cu113

Hello, I need detailed information about the model, and I would like to use torchinfo's summary function. Could you advise on where I should incorporate the following code? `from torchinfo...

Hello, I am interested in customizing the encoder used in your project. Specifically, I would like to know if it's possible to replace or modify the existing encoder implementation, which...

您好,很感谢您的工作,我使用了您的可视化代码,但是我有一个问题关于multi-scale features,据我所知,deformable detr,在encoder的操作之前,会将backbone出来的特征将H,W进行合并,然后将4维的多维特征进行铺平,然后再进行后续的操作得到feature,您这里的multi-scale feature的维度是LxBxCxHxW,请问您是将后续得到的的feature进行逆操作得到的吗,还是说我的理解有问题,期待您的回复。

/home/aigroup/chenzx/ws_internImage/bin/python3.8 /home/aigroup/chenzx/ws_internImage/code/Co-DETR/tools/deployment/pytorch2onnx.py /home/aigroup/chenzx/ws_internImage/lib/python3.8/site-packages/mmcv/__init__.py:20: UserWarning: On January 1, 2023, MMCV will release v2.0.0, in which it will remove components related to the training process and add a data transformation module. In...

I can't execute the setup.py. Even after I used this command, It still happen. ``` pip install torch ``` I don't know what to do ``` (Co-DETR-3.7.11) luckydipper@qhrqufucBookAir Co-DETR %...

![2](https://github.com/Sense-X/Co-DETR/assets/123863030/dfa11533-9a36-490d-ba1b-e5186f0a1200)

尊敬的作者大大您好,使用ViT-L训练模型,安装README将vit.py和sfp.py配置好之后,使用单卡训练出现下面的错误: KeyError: "CoDETR: 'ViT is not in the models registry'" 若使用分布式训练则出现下面的错误: TypeError: init_process_group() got an unexpected keyword argument 'port' 请问是什么原因呢?感谢指导!

Hello , I am trying to export `Co-DETR/projects/configs/co_dino/co_dino_5scale_swin_large_16e_o365tococo.py` to onnx using the file `tools/deployment/pytorch2onnx.py`, but when I run the file it tells me that **KeyError: 'CoDETR is not in the...