bywang2018

Hello, where can I download this dataset（coco_un_yolov4_55_0.5）? Thanks！ @xingyizhou

This is very important to me! Thank you very much! @xingyizhou

Thank you for your affirmation and praise for our work! I think the problem may occur in the compilation. Please refer to the usage section in README.md.

您好！可能是网页的问题，我在readme中添加了链接： 百度云：https://pan.baidu.com/s/1Q1afq9y0A61QwlCny4ALFQ Google Drive：https://drive.google.com/file/d/1UMq0CP20lKcraOTvsFMjiLjPfDam9jAp/view?usp=sharing

同学，你好！感谢你对我们工作的关注。论文相关的环境、代码、模型权重，我已经全部上传到github中了，可能需要你根据上面的说明进行搭建。 > 2023年5月31日 20:16，songsee ***@***.***> 写道： > > > 作者您好，我最近在做对比实验，但是由于环境等问题，代码难以复现，因此我想请求您能分享一下您的实验结果吗？我主要需要以下检测指标：mAP、Precision、Recall、模型参数量、Model size、FPS、GFLOPs；万分恳请您能分享这些实验结果，我将用于对比实验章节。如果作者方便的话，我想加一下您的联系方式，以供进一步交流。 > > 恳请作者回信。 > > — > Reply to this email directly, view it on GitHub , or unsubscribe...

Sorry to confuse you, but please note that our implementation is consistent with that in the paper. There are obvious differences between the proposed attention mechanism and the general attention...

ahh， Don’t mention it！ If you want to make the model lighter, I suggest you use a single-layer dense selective attention. Specifically, you can select a specific scale of a...

1. Sorry, I can't remember the version number clearly due to the time reason. However, I conduct the experiment on the latest mmdetection(mmdet version 2.3.0)， and our approach remains effective....

> 作者您好，请问一下数据集在下载过程中出现问题，area的值全为1.0，导致相关中物体和大物体检测不了，能否在提供一下数据集 Thank you for your attention to our work! The annotation file provides the coordinate value of the object, which can be used to calculate the area.

+1