-
Hello,
Can this code be used to train a model for Autoware's Point Pillars package ?
Thank you.
-
hello, Thanks for your work. I have a question about the point cloud range. we have done a lot of training with the original pointpillar, if I use point cloud range(pc range)==(-74.88, -74.88, -2, 7…
-
waymo dataset only have vehicle class,but large vehicles such as bus and truck are labeled vehicle. in hv_pointpillars_secfpn_waymo.py file,only anchor size of car is set as [2.08, 4.73, 1.77].I te…
-
> Implementation Details: We basically follow the implementation in the paper in terms of the network architecture (having a stride of 1 for the first convolutional block). Different settings of voxel…
-
@tianweiy is there any cpu version of the code available for inference ??
I am trying to build the inference part on cpu but det3d/ops/dcn and iou3dnms does not have cpu version files ? any thoughts…
-
Hi, sir. I am a newbie in 3D detection. I have download the detection result from [https://www.nuscenes.org/data/detection-pointpillars.zip](url) and I read the **pointpillars-test.json** and found th…
-
I tried to train CenterPoint on kitti， when finished training, the val result is far from expected.
Use PillarFeatureNet as feature extracter, second as backbone and second_fpn as neck, train on 3-cl…
-
environment： cuda11.0 pytorch:1.7.0 mmdetection3D:tag v0.10.0
I run "python ./tools/train.py ./configs/dynamic_voxelization/dv_pointpillars_secfpn_6x8_160e_kitti-3d-car.py ", then get error "Runtim…
-
File "/home/sl/.conda/envs/open-mmlab/lib/python3.7/site-packages/torch/distributed/distributed_c10d.py", line 187, in _check_default_pg
"Default process group is not initialized"
AssertionErr…
-
The paper of pointpillars uses ssd as detection head,
in mmedtection3d ssd is not used but Anchor3DHead instead.
am i right?
where i can find more information about Anchor3DHead , and its differ…