MapTR

MapTR copied to clipboard

![Uploading 1727079787550.jpg…]()

amazingpanpanda

During the model inference process, I found that there is a function int maptr.py named def extract_img_featm the content is: if self.use_grid_mask: img = self.grid_mask(img) I found that grid_mask is...

Kerwin0621

ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: -9) local_rank: 0 (pid: 1175722) of binary: .../envs/maptr/bin/python3

1

 I am having the following problem when training the fusion model. What might be the reason for this and how to fix it?

BatyrM

Nice work bro. What should I do if I want to use only one camera ('CAM_FRONT') to construct map

ztianlin

Hi author, there is a new dataset from Open Drive Lab which is called OpenLaneV2 which was built from NuScenes and AgoverseV2. They add some annotations for the task of...

BaophanN

we are training use our data, loss decrease very slow our input annotation is in lidar coord like this, but i think the nuscene is in ego coord, but in...

AnMoran

Thanks for your great work. when would you release the code for LaneGAP, which I did not find in this repo (directed from LaneGAP repo). Thanks!

Mollylulu

我使用4卡4090上训练maptr，nuscense数据集，出现以下报错，请问是什么原因呀 Traceback (most recent call last): File "./tools/train.py", line 260, in main() File "./tools/train.py", line 249, in main custom_train_model( File "/workspace/code/projects/mmdet3d_plugin/bevformer/apis/train.py", line 27, in custom_train_model custom_train_detector( File "/workspace/code/projects/mmdet3d_plugin/bevformer/apis/mmdet_train.py", line 75,...

youhha

 On the branch maptrv2，firstly I produce maptrv2 dataset using "python tools/maptrv2/custom_nusc_map_converter.py --root-path ./data/nuscenes --out-dir ./data/nuscenes --extra-tag nuscenes --version v1.0 --canbus ./data"； Then I execute this command，"bash ./tools/dist_test_map.sh ./projects/configs/maptrv2/maptrv2_nusc_r50_24ep.py ./ckpts/maptrv2/maptrv2_nusc_r50_24e.pth...

xiebinghua