Exception has occurred: ValueError
not enough values to unpack (expected 3, got 2)
File "/home/zephyr/openmmlab/mmdetection3d/projects/PETR/petr/petr_head.py", line 449, in forward
img_h, img_w, _ = img_metas[img_id]['img_shape'][cam_id]
Additional information
I use the nuscenes dataset and download the data_info.pkl from official website
According to my previous experience I am using the v2.0 dataset format, but the code is still supported for 1.0
The same issue, and it can be solved by change img_h, img_w, _ = img_metas[img_id]['img_shape'][cam_id] to img_h, img_w = img_metas[img_id]['img_shape'][cam_id]
Prerequisite
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
torch 1.13.1+cu116 pypi_0 pypi torchaudio 0.13.1+cu116 pypi_0 pypi torchvision 0.14.1+cu116 pypi_0 pypi mmcv 2.0.0rc4 pypi_0 pypi mmdet 3.1.0 dev_0
mmdet3d 1.3.0 dev_0
mmengine 0.9.0 dev_0
mmsegmentation 1.2.1 dev_0
Reproduces the problem - code sample
Reproduces the problem - command or script
Reproduces the problem - error message
Additional information