open-mmlab
[Bug] NuScenesDataset class name conflict with CenterHead
Prerequisite
- [X] I have searched Issues and Discussions but cannot get the expected help.
- [X] I have read the FAQ documentation but cannot get the expected help.
- [X] The bug has not been fixed in the latest version (dev-1.x) or latest version (dev-1.0).
Task
I'm using the official example scripts/configs for the officially supported tasks/models/datasets.
Branch
main branch https://github.com/open-mmlab/mmdetection3d
Environment
Name: mmdet3d Version: 1.3.0
Reproduces the problem - code sample
config use CenterHead: mmdetection3d-v1.3.0\configs_base_\models\centerpoint_pillar02_second_secfpn_nus.py
在NuScenesDataset类中以及create data.py中使用的类别顺序是
('car', 'truck', 'trailer', 'bus', 'construction_vehicle', 'bicycle','motorcycle', 'pedestrian', 'traffic_cone', 'barrier'),
但是在mmdetection3d-v1.3.0\mmdet3d\models\dense_heads\centerpoint_head.py 中 482行
如果使用多tasks的CenterHead，将会出现问题，因为在482行中是根据给定task中的class_names 索引加上flag来计算对应的class index。这个顺序和NuScenesDataset的顺序是不一致的，这个将会有问题。
之前0.18的版本中设置的 NuScenesDataset 类别顺序是('car', 'truck', 'construction_vehicle', 'bus', 'trailer', 'barrier', 'motorcycle', 'bicycle', 'pedestrian', 'traffic_cone'）则没问题
解决办法：可以在CenterHead中添加字段，用来输入数据集的顺序，计算索引的时候根据这个索引来获取对应的索引
type='CenterHead', in_channels=sum([128, 128, 128]), tasks=[ dict(num_class=1, class_names=['car']), dict(num_class=2, class_names=['truck', 'construction_vehicle']), dict(num_class=2, class_names=['bus', 'trailer']), dict(num_class=1, class_names=['barrier']), dict(num_class=2, class_names=['motorcycle', 'bicycle']), dict(num_class=2, class_names=['pedestrian', 'traffic_cone']), ],
Reproduces the problem - command or script
None
Reproduces the problem - error message
None
Additional information
No response
