search

Haiyang-W / RBGNet

[CVPR2022] This is the official code of "RBGNet: Ray-based Grouping for 3D Object Detection".
41 stars 4 forks source link

How do I run this network with my own data? #4

Open mostafa501 opened 10 months ago

mostafa501 commented 10 months ago

Dear all, thank you for publishing this work. I am curious how to use this network on my own data. For example, say I have a PCD for chairs, I do not have the ground truth for this. I just want to run inference script to give me a list of detected objects. How would be the best way to progress using your network? Any help on this would be very much appreciated. Thank you for the contribution !!

LIUXIN4558 commented 1 month ago

May I ask if you have successfully reproduced this code? I am currently experiencing this issue when reproducing it using the runrgbd dataset: **2024-07-25 16:03:37,464 INFO Loading SUNRGBD dataset Traceback (most recent call last): File "train.py", line 204, in main() File "train.py", line 105, in main train_set, train_loader, train_sampler = build_dataloader( File "/home/ipsg2/code/lx2/RBGNet/tools/../pcdet/datasets/init__.py", line 54, in build_dataloader dataset = all[dataset_cfg.DATASET]( File "/home/ipsg2/code/lx2/RBGNet/tools/../pcdet/datasets/sunrgbd/sunrgbd_dataset.py", line 29, in init self.include_sunrgbd_data(self.mode) File "/home/ipsg2/code/lx2/RBGNet/tools/../pcdet/datasets/sunrgbd/sunrgbd_dataset.py", line 51, in include_sunrgbd_data sample_id_list.extend([info['point_cloud']['lidar_idx'] for info in infos]) File "/home/ipsg2/code/lx2/RBGNet/tools/../pcdet/datasets/sunrgbd/sunrgbd_dataset.py", line 51, in sample_id_list.extend([info['point_cloud']['lidaridx'] for info in infos]) TypeError: string indices must be integers**_ I have checked the. pkl file and it does not contain 'point_cloud' and 'lidar idx' May I ask if you have encountered such a problem?

Haiyang-W commented 1 month ago

Sorry for the late reply. Please refer to here for generating your own dataset. Note that the coordinate system adopted in MMdetection3D(0.15) is very different from MMdetection3D(>=1.0).