LoGoNet
LoGoNet copied to clipboard
PJLab-ADG
[CVPR2023] LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusion
Why is the code particularly slow to load during training? Have you ever encountered this situation？
In the process of debugging code, it takes a long time to load after each training run, about 5 minutes, and it gets stuck in the following interface. Is there...
When I debug for /detection/tools/train.py file, there has an error "'SwinTransformer is not in the backbone registry'". It this caused by version of mmdet or mmcv-full? Following is my environment...
I run the demo.py by python demo.py --cfg_file /media/wdr/cym/LoGoNet-base/detection/tools/cfgs/det_model_cfgs/kitti/LoGoNet-kitti.yaml --data_path /media/wdr/cym/LoGoNet-base/detection/data/kitti/testing/velodyne/000000.bin --ckpt /media/wdr/cym/LoGoNet-base/checkpoint_epoch_40.pth and output error: 2024-04-02 22:12:25,115 INFO -----------------Quick Demo of al3d-det------------------------- Traceback (most recent call last): File "demo.py",...
Hello, I would like to run the code on waymo dataset. However, when I run the following two commands 1. "python -m al3d_det.datasets.waymo.waymo_preprocess --cfg_file tools/cfgs/det_dataset_cfgs/waymo_xxx_sweeps_mm.yaml --func create_waymo_infos", 2. python -m...
I followed the instructions in INSTALL and I created a env based on python=3.6,when I want to train in KITTI,the error happened. I searched on google and they told me...
assert img_file.exists() AttributeError: 'NoneType' object has no attribute 'exists' run ‘python -m al3d_det.datasets.waymo.waymo_preprocess --cfg_file tools/cfgs/det_dataset_cfgs/waymo_xxx_sweeps_mm.yaml --func create_waymo_infos' and 'python -m al3d_det.datasets.waymo.waymo_preprocess --cfg_file tools/cfgs/det_dataset_cfgs/waymo_xxxx_sweeps_mm.yaml --func create_waymo_database'. There are not the path...
Thanks for your contribution, can you tell me how to visualize the kpl file of the test results？
hello，I have a question that where are the GoF and LoF codes in kitti's code？ I have seen the code in LoGoHead_kitti.py localgrid_densityfeat_fuse = self.crossattention_pointhead(batch_dict, point_features=localgrid_densityfeat, point_coords=grid_coords, layer_name="layer1") Is this...
hello im using ubuntu 22 and cuda 11.8. I cant install requirements for example sklearn library and torch_scatter. Do you have maybe already created environment in conda and could send...
