Closed Shaoqing26 closed 3 years ago
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.
The training and evaluation code for instance segmentation is
train.py
andtest.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.
Close due to inactivity.
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?