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

初学者问题,在运行run_benchmark.py时报错 #30

Open
gwgc opened this issue Jan 14, 2024 · 3 comments
Open

初学者问题,在运行run_benchmark.py时报错 #30

gwgc opened this issue Jan 14, 2024 · 3 comments

Comments

@gwgc
Copy link

gwgc commented Jan 14, 2024

运行run_benchmark.py时报错:提示No module named 'lib.model_test'
请问这是哪个库没有安装吗?在网上没有查到对应的库。谢谢!

(base) root@xr-Virtual-Machine:~/miniconda3/condabin/xrlocalization# python3 run_benchmark.py --map_path /root/xrloc-test-meta/map --query_path /root/xrloc-test-meta/query.txt
[01/14/2024 20:22:26 INFO] Dataset size: 3
[01/14/2024 20:22:26 INFO] ==================================================
[01/14/2024 20:22:26 INFO] ***************** XRLocalization *****************
[01/14/2024 20:22:26 INFO] ==================================================
Traceback (most recent call last):
File "run_benchmark.py", line 52, in
main(args.query_path, args.map_path, args.json)
File "run_benchmark.py", line 20, in main
loc = Localizer(map_path)
File "/root/miniconda3/condabin/xrlocalization/xrloc/localizer.py", line 57, in init
self.lextractor = Extractor(self.config['local_feature'])
File "/root/miniconda3/condabin/xrlocalization/xrloc/features/extractor.py", line 38, in init
model = self.make_model(name)
File "/root/miniconda3/condabin/xrlocalization/xrloc/features/extractor.py", line 106, in make_model
module = import(module_path, fromlist=[''])
File "/root/miniconda3/condabin/xrlocalization/xrloc/features/d2net.py", line 10, in
from lib.model_test import D2Net as D2N
ModuleNotFoundError: No module named 'lib.model_test'

@HailinYu0414
Copy link
Member

You did not pull the 3rdparty dependencies. Try cd xrlocalization & git submodule update --init --recursive

@gwgc
Copy link
Author

gwgc commented Mar 3, 2024

感谢您的回复,重新安装了乌班图系统,已经可以运行run_benchmark.py了。但是在学习下一步又出现了新问题,在Benchmark Evaluation章节,“0. Generate localization map“生成本地化地图,参考Generate localization map章节中。先要通过xrloc生成Re-triangulation吗?
在“Re-triangulation by [xrloc]”的链接中要对自己拍摄的图片进行处理吗?原文中的这段话如何理解,准备自己的图片,cameras.bin、images.bin、points3D.bin这几个文件是通过图片生成的吗。
Assume we have reference images and the sparse model that is COLMAP format:
+---images/
| |-- ...
+---model/
|--cameras.bin
|--images.bin
|--points3D.bin

@HailinYu0414
Copy link
Member

Re-triangulation那一步要使用xrloc和xrsfm配合完成。具体流程是先使用xrloc对参考图像使用指定特征进行特征抽取、特征匹配,然后再运行xrsfm中的三角化工具。

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