Skip to content

Train stage 1 error on nuscenesdata #12

@Styiving

Description

@Styiving

Dear Author,
I am writing to express my sincere gratitude for your valuable contributions to the open-source community. Your work has been extremely helpful and inspiring.
However, I encountered an issue while running the following command:
CUDA_VISIBLE_DEVICES=0,1 python train.py experiment=multi_view_stage_1_cam_rect trainer.devices=2 extras.mini_dataset=False
During the execution, I received the following error message:
TypeError: get_single_image() takes 2 positional arguments but 6 were given
The error occurred at the following location in the code:

File "/data/tianshan/BEVGen-training/multi_view_generation/bev_utils/nuscenes_dataset.py", line 847, in getitem
data = {**data, **self.get_cam(*record)}
File "/data/tianshan/BEVGen-training/multi_view_generation/bev_utils/nuscenes_dataset.py", line 735, in get_cam
ret = self.get_single_image(*args)
I have carefully reviewed the code and it seems that the get_single_image() function is being called with more arguments than it expects. I believe this might be due to a mismatch between the expected number of arguments and the actual number of arguments being passed.
I would be very grateful if you could provide some guidance on how to resolve this issue. If there is any additional information you need from me, please let me know.
Thank you once again for your time and effort. I look forward to your response.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions