[Docs] How to run the demo ?

[BetterYimi]

Branch

main branch https://mmdetection3d.readthedocs.io/en/latest/

📚 The doc issue

I used 'configs/detection/mv-det3d_8xb4_embodiedscan-3d-284class-9dof.py' , 'mv-3ddet.pth' provided by you, and your simple dataset office to test demo.ipynb. but I can only get one picture of the results, the length of results in results = model.test_step(collate_data) is 1

Suggest a potential alternative/fix

No response

[4mm7]

I have encountered an issue similar to one you previously experienced. I am reaching out to inquire about how you resolved it.Could you please share any insights or solutions you found for the issue?

[4mm7]

@BetterYimi Excuse me, I encountered a similar problem to #21 when running the demo.py script. Upon inspecting the model output, I noticed that len(results) is 1, which resulted in only one image being visualized, with the boxes stacked on top of each other. However, that issue has already been closed. I'm unsure how to resolve this situation.If you can provide assistance, that would be great.

[BetterYimi]

@4mm7 我是简单将代码中的len(results)改为了1-len(n_frames)，同时将boxes, labels = nms_filter(results[i].pred_instances_3d)改为了boxes, labels = nms_filter(results[0].pred_instances_3d)

[xiaolu-luu]

@4mm7 我是简单将代码中的len(results)改为了1-len(n_frames)，同时将boxes, labels = nms_filter(results[i].pred_instances_3d)改为了boxes, labels = nms_filter(results[0].pred_instances_3d)

可以详细说一下如何操作吗？哪里的len(results)改为了1-len(n_frames)，感谢！！！