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

标注的kitti格式数据在OpenPCDet下训练报错: ValueError: Caught ValueError in DataLoader worker process 0. ValueError: need at least one array to stack #193

Open
wanzghen0123 opened this issue Apr 18, 2024 · 5 comments

Comments

@wanzghen0123
Copy link

作者你好, 标注完成的KITTI格式数据,在OpenPCDet下训练报错. 而原始的kitti数据集没有问题.
报错信息如下:
OpenPCDet/lib/python3.8/site-packages/torch/_utils.py", line 429, in reraise
raise self.exc_type(msg)
ValueError: Caught ValueError in DataLoader worker process 0.
...
/OpenPCDet/lib/python3.8/site-packages/numpy/core/shape_base.py", line 460, in stack
raise ValueError('need at least one array to stack')
ValueError: need at least one array to stack
帮忙看一下?
(就相当与重新标注了kitti数据,把json转换成txt标签)

@naurril
Copy link
Owner

naurril commented Apr 19, 2024

是不是标注内容是空的?

@wanzghen0123
Copy link
Author

是不是标注内容是空的?

不是.作者你好,我现在遇到的问题是,在该标注工具下,标注的kitti格式的数据,在OpenPCDet框架下,训练centerpoint/pointpillar模型,需要将模型配置文件里面的参数:
PREPARE: {
filter_by_min_points: ['Car:0', 'Pedestrian:0', 'Cyclist:0'],
filter_by_difficulty: [-1],
}和
SAMPLE_GROUPS: ['Car:0','Pedestrian:0', 'Cyclist:0']
都置0,才能训练.训练完成,各项指标均为0.
我的操作流程是:
(1)将自采集数据转到kitti坐标系下(取一帧,然后复制100份)
(2)在SUSTechPoint工具下打开该数据(bin文件的点云, 标定文件, 前视相机的图片),进行标注,然后将json的标签文件转为kitti所需的txt文件.
(3)将此100帧数据同时作为训练集和测试集.在OpenPCDet框架下,进行kitti格式数据集划分.
(4)进行训练
训练指标均为0.
同样的步骤,我直接拷贝的kitti数据集的000000.bin数据进行sustech工具的标注,然后划分数据集训练和测试,结果同上.(指标为0)
原始的kitti数据集则可以正常训练和测试,指标也是正常的.
不知道问题出在哪里???是不是,sustechpoint工具的kitti格式数据转换有问题,现在还在定位中.

@naurril
Copy link
Owner

naurril commented Apr 23, 2024 via email

@wanzghen0123
Copy link
Author

wanzghen0123 commented Apr 24, 2024 via email

@wanzghen0123
Copy link
Author

wanzghen0123 commented Apr 24, 2024 via email

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