Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Dota的test数据集复现mAP过低 #39

Open
wheremyfu opened this issue Jul 19, 2024 · 3 comments
Open

Dota的test数据集复现mAP过低 #39

wheremyfu opened this issue Jul 19, 2024 · 3 comments

Comments

@wheremyfu
Copy link

我使用仓库主页提供的训练好的模型以及配置文件对Dota的test数据集进行推理,但是结果mAP仅有0.39.
下图为我所用的模型:
image

配置文件:
image

测试指令:
CUDA_VISIBLE_DEVICES=0 python /home/pp/OBBDetection/tools/test.py '/home/pp/Remote-Sensing-RVSA/Object Detection/configs/obb/oriented_rcnn/vit_base_win/faster_rcnn_orpn_our_rsp_vitae-nc-base-win-rvsa_v3_kvdiff_wsz7_fpn_1x_dota10_lr1e-4_ldr75_dpr15.py' '/home/pp/Model/vite_b_RSVA_kvdiff_ls/vitae_rvsa_kvdiff.pth' --format-only --show-dir '/home/pp/Model/vite_b_RSVA_kvdiff_ls/work_dirs/save' --options save_dir='/home/pp/Model/vite_b_RSVA_kvdiff_ls/work_dirs/save_val' nproc=1

提交给dota官方评估的结果:
test

@wheremyfu
Copy link
Author

同时我查阅了https://github.com/ViTAE-Transformer/Remote-Sensing-RVSA/issues/33以及https://github.com/ViTAE-Transformer/Remote-Sensing-RVSA/issues/19

我在测试过程中虽然出现,但未影响测试运行
image

我同样在_init_.py补齐所需的模型文件,但有一个始终未找到,所以我将它剔除了
image

@wheremyfu
Copy link
Author

希我想知道我的复现过程是否有不恰当的地方呢?可能是有什么原因造成的?

@DotWang
Copy link
Collaborator

DotWang commented Jul 19, 2024

@wheremyfu kvdiff这个好像我后来改过什么东西了,但是时间有点长了,我忘了,不过我感觉应该不会掉这么多点,你先试一下不是kvdiff的,别人论文里边一般对比方法写我们的也都是用不是kvdiff的那个,如果没有问题,那可能就是之前改的东西的原因,如果依然精度很低,那就是你复现步骤的问题

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants