OpenPCDet icon indicating copy to clipboard operation
OpenPCDet copied to clipboard

OpenPCDet Toolbox for LiDAR-based 3D Object Detection.

Results 171 OpenPCDet issues
Sort by recently updated
recently updated
newest added

Hi there, I trained a model and wanted to open the result.pkl file generated by train.py. `import torch` `res = torch.load("/path.../result.pkl")` `print(res)` but i get the error: `RuntimeError: Invalid magic...

I used the pre-trained model of pointpillars to continue training on kitti, but the AP on the validation set dropped by 6-7.Why is this? 2022-07-05 17:11:15,104 INFO **********************Start logging********************** 2022-07-05...

I want to visualize the point cloud data with bounding boxes and the corresponding image bounding boxes at the same time in order to better observe the quality of the...

add single frame ros inference script (currently only test on PVRCNN model) depends: rospy ros_numpy pyquaternion and etc...

How to fix this problem? I am using PVRCNN to test on my 32 beam dataset, pretrained by Pandaset 64 beam. ![image](https://user-images.githubusercontent.com/52599722/170453506-666081f5-b002-4ddb-b48b-52c728f2a550.png)

Hello, dear author, i have tried to run 3Dssd model on the nescenes dataset but just get very low map of around 20%(in the paper, the result is 42.66%), could...

This config file is modified from both [official code released for KITTI](https://github.com/tianweiy/CenterPoint-KITTI) and [OpenPCDet version for WAYMO](https://github.com/open-mmlab/OpenPCDet/blob/master/tools/cfgs/waymo_models/centerpoint_without_resnet.yaml). And if anyone wants to get a pre-training model, please let me know....

is there any reason that why pointpillars does not use sponv? Does it drop accuracy?

Hi, Actually i need to implement the VFE encoder based on the paper "SECOND: Sparsely Embedded Convolutional". Looking into the codebase "/workspace/OpenPCDet/pcdet/models/backbones_3d/vfe/mean_vfe.py" it only takes the mean of point clouds...

I'm trying to set up the but keep getting this extensive error message which i can't seem to resolve. I have CUDA 11.4 installed on my system and the following...