Skip to content

[Docs] EmbodiedScan v2 beta have no 'embodiedscan_[train or val]_mini_vg'聽#93

Description

@Fan123456-c

Branch

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

馃摎 The doc issue

Hi, thank you for releasing 'EmbodiedScan v2 beta'. But I have a question.
In EmbodiedScan v1 dataset files, it has:
image
But In EmbodiedScan v2 dataset files, it has:
image
So, how could I train a 3D grounding task with a mini-dataset in the v2 dataset?

Suggest a potential alternative/fix

No response

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

Labels

No labels
No labels

Type

No type

Projects

No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions