Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Semantic segmentation on nuImage dataset #402

Closed
Shaoqing26 opened this issue Apr 1, 2021 · 3 comments
Closed

Semantic segmentation on nuImage dataset #402

Shaoqing26 opened this issue Apr 1, 2021 · 3 comments

Comments

@Shaoqing26
Copy link

First,Thanks the exllent job in this open source project.
and ,I found there has only have instance segmantation on nuImage dataset,and few training details,but semantic segmantation semantic is also popular and helpful reserch work,is there has any plan to add semantic segmentation modals?

also there have no training and evaluation code for nuImage dataset,is will complete it recently?

@ZwwWayne
Copy link
Collaborator

ZwwWayne commented Apr 3, 2021

The training and evaluation code for instance segmentation is train.py and test.py. You can use them to train/test nuImages models as other 3D detectors in MMDet3D because MMDet3D inherits MMDet.
For semantic segmentation, we will release examples this month, using MMSegmentation. Please stay tuned.

@yezhen17
Copy link
Collaborator

yezhen17 commented Apr 3, 2021

The training and evaluation code for instance segmentation is train.py and test.py. You can use them to train/test nuImages models as other 3D detectors in MMDet3D because MMDet3D inherits MMDet.
For semantic segmentation, we will release examples this month, using MMSegmentation. Please stay tuned.

As to help you understand how this works, please note that our train.py uses a function build_detector. This function consists of build from mmdet, which uses MMCV Registry. Please then refer to the tutorial of MMCV Registry.

@Tai-Wang
Copy link
Member

Tai-Wang commented Apr 8, 2021

Close due to inactivity.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants